{ "data": { "a": { "slug": "carbon-x", "name": "Carbon-X", "vendor": "Hugging Face (HuggingFaceBio)", "vendorUrl": "https://huggingface.co/HuggingFaceBio", "kind": "weights", "category": "open-weights", "summary": "Carbon-X is Hugging Face's open-weight 14.8B language model for DNA, a fine-tune of Qwen3-14B that reads raw DNA in a chat and answers in English about variant effects and regulatory regions, with a 40,960-token context, under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/carbon-x", "markdownUrl": "https://www.anchorterminal.com/tools/carbon-x.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/carbon-x.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/carbon-x.json", "dns": "carbon-x.grade.anchorterminal.com", "repo": "https://huggingface.co/HuggingFaceBio/Carbon-X", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "HuggingFaceBio/Carbon-X" }, { "registry": "huggingface", "name": "HuggingFaceBio/Carbon-X-GGUF" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The Hub reports gated false for HuggingFaceBio/Carbon-X and HuggingFaceBio/Carbon-X-GGUF (checked 2026-10-23). The Python tokenizer fetches Qwen/Qwen3-4B-Base's tokenizer at a pinned revision on first load, which is also ungated.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0, and the base Qwen3-14B is Apache 2.0 too. Hugging Face sells no per-call access to it and no inference provider serves it. Running it costs the hardware, 29.6 GB for the BF16 safetensors and 9.6 GB for the publisher's smallest GGUF, Q4_K_M (checked 2026-10-23).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-23).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-23" }, "docsUrl": "https://huggingface.co/HuggingFaceBio/Carbon-X", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "dna", "genomics", "biology", "fine-tune", "apache-2.0", "safetensors", "gguf", "self-hosted" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1350, "categoryRank": 32, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 35, "reach": 90, "risk": 65, "upkeep": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-03" }, "negative": 0, "verdict": "A DNA specialist cousin that another agent calls for variant-effect and sequence questions, with DNA kept on the machine. Hugging Face's Q4_K_M GGUF needs about 12 GB and Q8_0 about 19 GB, on llama.cpp b11742 or later. It isn't clinically validated, isn't trained for tool calls or reasoning, and its Python tokenizer runs repository code.", "bestFor": "Agents that need a second opinion on DNA variants and regulatory regions on a 16 to 24 GB machine, without sending sequences to a hosted model.", "strengths": [ "Hugging Face's own GGUFs at four precisions, the smallest about 12 GB with a fifth added", "Runs in released llama.cpp, vLLM, SGLang and Transformers", "Apache 2.0 on the model and its Qwen3-14B base, nothing gated", "A ready-made skill, an OpenAI-style tool example and an Inspect example for calling it from another agent", "Mid-training data listed by source with shares of 302B tokens" ], "weaknesses": [ "Not clinically validated and no wet-lab validation reported", "The Python tokenizer needs trust_remote_code, and llama.cpp before b11742 tokenizes DNA wrongly", "Not trained for tool calling, structured output or reasoning", "tokenizer_config.json gives 131,072 tokens as model_max_length while the card and config give 40,960", "No inference provider or hosted API, and no knowledge cut-off" ], "agentNotes": [ "Quickest start is `llama-server -hf HuggingFaceBio/Carbon-X-GGUF:Q8_0 -ngl 99 -c 40960 --jinja --chat-template-kwargs '{\"enable_thinking\": false}' --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0`, on llama.cpp b11742 or later", "With vLLM or Transformers pass trust_remote_code, and expect the tokenizer to fetch Qwen/Qwen3-4B-Base at a pinned revision on first load", "Keep enable_thinking false and the card's sampling (temperature 0.6, top_p 0.95, top_k 20), the settings every reported result used", "Keep DNA in files and pass sequences by name, compute positions and base changes in code and send them as context, the card says the model miscounts long sequences", "Only A, C, G and T form 6-mers, so filter N and other IUPAC codes first or they become a single oov token", "Strip the dna tags from answers if you need bare sequence, llama.cpp keeps them in the text", "Cap max_tokens for next-base questions, long DNA generation is slow and degrades" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 35, "reach": 90, "risk": 65, "upkeep": 72 }, "provenanceScore": 61, "checked": { "categories": { "interface": "2026-11-03", "reach": "2026-11-03", "risk": "2026-11-03", "upkeep": "2026-11-03" }, "last": "2026-11-03", "lastMoved": "2026-11-03", "oldest": "2026-11-03", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# llama.cpp b11742 or later (older builds tokenize DNA wrongly):\nllama-server -hf HuggingFaceBio/Carbon-X-GGUF:Q8_0 -ngl 99 -c 40960 --jinja \\\n --chat-template-kwargs '{\"enable_thinking\": false}' \\\n --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0 --port 8080\n# or, with vLLM:\nvllm serve HuggingFaceBio/Carbon-X --trust-remote-code", "http": "curl http://localhost:8080/v1/chat/completions -H 'Content-Type: application/json' \\\n -d '{\"messages\": [{\"role\": \"user\", \"content\": \"Is this sequence more likely coding or non-coding? ATGGCGCTGTGGATGCGCCTCCTG\"}]}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/carbon-x" }, "sameCompany": [ "hugging-face-inference-endpoints", "smollm3-3b" ], "weights": { "trainedBy": "Hugging Face with Zhongguancun Academy and TIGEM / University of Naples Federico II", "builtOn": "Qwen/Qwen3-14B (vocabulary extension, mid-training, supervised fine-tune and GRPO; base Apache 2.0, declared in the card's metadata)", "params": "14.8B", "context": 40960, "goodFor": "A DNA specialist another agent calls, for variant-effect questions, regulatory regions and next-base prediction on raw DNA kept on local hardware.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Carbon-X-GGUF Q4_K_M", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X-GGUF", "who": "publisher", "precision": "q4_k_m", "sizeGB": 9.64, "memoryGB": 12, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "carbon-x-q4_k_m.gguf, 9,636,318,080 bytes. Embedding and output tensors stay at Q8_0. The publisher's own runs put it lowest of the builds on FrontierVEP (67.8) and NextBase (38.6)" }, { "name": "Carbon-X-GGUF Q6_K", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X-GGUF", "who": "publisher", "precision": "q6_k", "sizeGB": 12.56, "memoryGB": 16, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "carbon-x-q6_k.gguf, 12,555,946,880 bytes" }, { "name": "Carbon-X-GGUF Q5_K_M", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X-GGUF", "who": "publisher", "precision": "q5_k_m", "sizeGB": 11.05, "memoryGB": 16, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "carbon-x-q5_k_m.gguf, 11,051,895,680 bytes" }, { "name": "Carbon-X-GGUF Q8_0", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X-GGUF", "who": "publisher", "precision": "q8_0", "sizeGB": 15.76, "memoryGB": 24, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "carbon-x-q8_0.gguf, 15,755,742,080 bytes, the build the publisher recommends" }, { "name": "Carbon-X", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X", "who": "publisher", "precision": "bf16", "sizeGB": 29.64, "memoryGB": 48, "format": "safetensors", "runsOn": [ "vLLM", "Transformers" ], "note": "Needs trust_remote_code for the custom HybridDNATokenizer, and Transformers v5 or later. The card says it fits one 80 GB GPU" }, { "name": "Carbon-X-GGUF BF16", "url": "https://huggingface.co/HuggingFaceBio/Carbon-X-GGUF", "who": "publisher", "precision": "bf16", "sizeGB": 29.65, "memoryGB": 48, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "carbon-x-bf16.gguf, 29,651,012,480 bytes. llama.cpp b11742 or later" } ], "run": "llama-server -hf HuggingFaceBio/Carbon-X-GGUF:Q8_0 -ngl 99 -c 40960 --jinja --chat-template-kwargs '{\"enable_thinking\": false}' --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0 --port 8080", "runBuild": "Carbon-X-GGUF Q8_0", "checked": "2026-10-23", "minMemoryGB": 12 }, "family": { "lab": "Hugging Face (Carbon)", "family": "Carbon", "url": "https://www.anchorterminal.com/open-weights/#huggingface-bio", "others": [ { "name": "Carbon-A-1.2B", "url": "https://huggingface.co/HuggingFaceBio/Carbon-A-1.2B", "params": "1.2B" }, { "name": "Carbon-8B", "url": "https://huggingface.co/HuggingFaceBio/Carbon-8B", "params": "8.3B" }, { "name": "Carbon-3B", "url": "https://huggingface.co/HuggingFaceBio/Carbon-3B", "params": "3.5B" }, { "name": "Carbon-500M", "url": "https://huggingface.co/HuggingFaceBio/Carbon-500M", "params": "0.5B" } ] }, "area": "models", "provenance": { "legalEntity": "Hugging Face (the HuggingFaceBio organisation, named Hugging Face Biology Research on the Hub)", "domain": "huggingface.co", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "valid", "checked": "2026-11-03", "notes": [ "The HuggingFaceBio organisation isn't verified on the Hub. It has 27 members, Hugging Face staff among them, and the huggingface/carbon GitHub repository links its Carbon models.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "huggingface.co/.well-known/security.txt names a security contact and expires in 2030.", "No changelog. The main repository's history shows five commits from 22 to 29 October 2026, the first a squashed upload; the merged pull requests show earlier commits on 21 and 22 October. Registration of huggingface.co wasn't checked." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/carbon-x.json", "live": { "slug": "carbon-x", "securityTxt": { "url": "https://huggingface.co/.well-known/security.txt", "state": "valid", "expires": "2030-07-01T08:42:00.000Z", "checkedAt": "2026-11-04T15:53:05.802458295Z" }, "domain": { "domain": "huggingface.co", "checkedAt": "2026-11-01T14:09:00.477589213Z" }, "updatedAt": "2026-11-04T15:53:05.802458295Z" } }, "answer": "Carbon-X scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Ripple-65B Preview leads on agent interface.", "b": { "slug": "ripple-65b-preview", "name": "Ripple-65B Preview", "vendor": "Ricursive Intelligence", "vendorUrl": "https://www.ricursive.com/ripple", "kind": "weights", "category": "open-weights", "summary": "Ricursive Intelligence's 65B dense model, pretrained from scratch and post-trained for agentic coding, on Hugging Face in BF16 and NVFP4 under Apache 2.0. Its custom architecture needs Ricursive's own model code to run.", "url": "https://www.anchorterminal.com/tools/ripple-65b-preview", "markdownUrl": "https://www.anchorterminal.com/tools/ripple-65b-preview.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ripple-65b-preview.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ripple-65b-preview.json", "dns": "ripple-65b-preview.grade.anchorterminal.com", "repo": "https://huggingface.co/ricursiveAI/Ripple-65B-Preview", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "ricursiveAI/Ripple-65B-Preview" }, { "registry": "huggingface", "name": "ricursiveAI/Ripple-65B-Preview-NVFP4" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither the BF16 nor the NVFP4 repository is gated (checked 2026-11-04).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it yourself costs the hardware, 129.6 GB for the BF16 files and 57.2 GB for the NVFP4 build by the Hub's file pages. Ricursive's launch post names Together AI, GMI Cloud and OpenRouter as hosts, but Together's model page says coming soon (checked 2026-11-04).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-04).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-04" }, "docsUrl": "https://huggingface.co/ricursiveAI/Ripple-65B-Preview", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "reasoning", "tool-calling", "coding", "apache-2.0", "safetensors", "remote-code", "self-hosted", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 53.3, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1350, "categoryRank": 78, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 75, "reach": 45, "risk": 55, "upkeep": 49 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-04" }, "negative": 0, "verdict": "A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.", "bestFor": "Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.", "strengths": [ "Apache 2.0 with nothing added, ungated, from the organisation Ricursive's site links to", "A tools-aware chat template with several calls a turn, and a server that returns reasoning, content and tool calls separately", "Trained for long context at 2M-token sequences, with 1M stated", "Base model and a speculative-decoding draft published beside the instruct model", "Safetensors only, with a checksum on every file" ], "weaknesses": [ "No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code", "The smallest build is 57.2 GB NVFP4, for NVIDIA Blackwell only, and there is no GGUF", "No independent benchmark yet, and the top-ranking claim rests on Ricursive's own Terminal-Bench 2.1 run", "Thinking can't be turned off or budgeted", "No safety guidance for agent use, no security contact and no knowledge cut-off" ], "agentNotes": [ "Run Ricursive's launcher from inference/server with `uv run --script serve.py` on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default", "The launcher turns on `--reasoning-parser ripple` and `--tool-call-parser ripple`; without them tool calls come back as raw text inside tool_call tags", "For `tool_choice: \"required\"` set `strict: true` and `additionalProperties: false` on each function, which the README says stopped extra argument fields", "Leave room in `max_tokens` for reasoning as well as the answer, since thinking is always on", "Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.3 } ], "editorialScores": { "interface": 75, "reach": 45, "risk": 55, "upkeep": 49 }, "provenanceScore": 36, "checked": { "categories": { "interface": "2026-11-04", "reach": "2026-11-04", "risk": "2026-11-04", "upkeep": "2026-11-04" }, "last": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "hf download ricursiveAI/Ripple-65B-Preview --local-dir ./ripple-65b\nhf download ricursiveAI/Ripple-65B-Preview-DFlash2 --local-dir ./ripple-dflash2\ncd ripple-65b/inference/server\nCUDA_VISIBLE_DEVICES=0,1 uv run --script serve.py \\\n --model-path ../.. \\\n --speculative-draft-model-path ../../../ripple-dflash2", "http": "curl http://127.0.0.1:30000/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\"model\": \"ripple\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}], \"max_tokens\": 128}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/ripple-65b-preview" }, "weights": { "trainedBy": "Ricursive Intelligence", "params": "65B", "context": 1048576, "goodFor": "A dense 65B model post-trained for agentic coding and terminal work, with several tool calls a turn and a long context, for teams with Blackwell GPUs or a DGX Spark.", "runtimes": [], "builds": [ { "name": "Ripple-65B-Preview-NVFP4", "url": "https://huggingface.co/ricursiveAI/Ripple-65B-Preview-NVFP4", "who": "publisher", "precision": "nvfp4", "sizeGB": 57.2, "memoryGB": 69, "format": "safetensors", "note": "NVFP4 MLP weights and activations with BF16 attention, 6 shards summed from the Hub's file page. For NVIDIA Blackwell, with Ricursive's DGX Spark loader. The checkpoint was replaced in place on release day" }, { "name": "Ripple-65B-Preview", "url": "https://huggingface.co/ricursiveAI/Ripple-65B-Preview", "who": "publisher", "precision": "bf16", "sizeGB": 129.6, "memoryGB": 160, "format": "safetensors", "note": "16 shards summed from the Hub's file page. Served with Ricursive's SGLang 0.5.19 plugin on two B200 GPUs" } ], "run": "CUDA_VISIBLE_DEVICES=0,1 uv run --script serve.py --model-path /path/to/Ripple-65B-Preview --speculative-draft-model-path /path/to/Ripple-65B-Preview-DFlash2", "runBuild": "Ripple-65B-Preview", "checked": "2026-11-04", "minMemoryGB": 69 }, "area": "models", "provenance": { "legalEntity": "Ricursive Intelligence, Inc.", "domain": "ricursive.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://huggingface.co/ricursiveAI/Ripple-65B-Preview/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "Every page on www.ricursive.com ends with \"© 2026 Ricursive Intelligence, Inc.\". The site links the Hugging Face organisation ricursiveAI (fullname Ricursive Intelligence), which publishes the four Ripple repositories. RDAP wasn't queried, by the run's rules.", "The Apache 2.0 LICENSE in the repository governs the weights and stands in for terms of service. The site's own legal pages (/legal and /legal/terms, titled Model Attribution Terms) render their text by script only and couldn't be read.", "Nothing is hosted by Ricursive, so no privacy policy or status page is scored.", "No changelog. The repositories' commit messages are uploads and one in-place swap of the NVFP4 checkpoint on release day.", "www.ricursive.com/.well-known/security.txt is 404 on 4 November 2026, and the only contact on the card and site is a general one." ], "score": 36 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ripple-65b-preview.json" }, "edges": [ { "by": 45, "category": "reach", "leads": "carbon-x", "name": "Reach", "reasons": { "a": "Memory 30, the publisher's Q4_K_M GGUF is 9.6 GB, or 11.6 GB with a fifth added. Runtimes 20, released llama.cpp (from b11742, which added the DNA tokenizer), vLLM, SGLang and Transformers all run it, with no Ollama or LM Studio entry. Builds 15, Hugging Face publishes GGUFs at four precisions. Terms 15, Apache 2.0 on the model and on its Qwen3-14B base. Download 10, nothing is gated. Hosted 0, no inference provider or Hugging Face API serves it.", "b": "Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read." }, "scores": { "a": 90, "b": 45 } }, { "by": 40, "category": "interface", "leads": "ripple-65b-preview", "name": "Agent interface", "reasons": { "a": "Chat template 20, a Jinja file in the repository. Tool-calling format 10, only the inherited template shows the format and no parser is named. Trained tool calling 0, nothing says it was trained to call tools. Structured output 0, not documented. Reasoning control 0, thinking can be switched off but was never trained, and the card asks you to keep it off. Context 5, 40,960 tokens from the base, though Hugging Face trained at 8,192 and under 16K. Most of what the card documents for agents is Carbon-X as a tool another model calls, which this checklist doesn't read.", "b": "Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M." }, "scores": { "a": 35, "b": 75 } }, { "by": 23, "category": "upkeep", "leads": "carbon-x", "name": "Documentation and upkeep", "reasons": { "a": "Model card 17, everything but a knowledge cut-off. Training data 15, the mid-training sources and shares are listed, the instruction and fine-tuning data aren't named, and there's no cut-off. Last change 20, 28 October 2026, when config.json, generation_config.json, tokenizer_config.json and tokenizer.py were fixed. Responsiveness 10, organisation members replied to 2 of the 4 questions so far. Version policy 5, a first release whose history was squashed without a note. File health 5, the card now sends llama.cpp users to the publisher's GGUF repository, but the tokenizer config's 131,072 still contradicts the card's 40,960. 17 + 15 + 20 + 10 + 5 + 5 = 72.", "b": "Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M." }, "scores": { "a": 72, "b": 49 } }, { "by": 10, "category": "risk", "leads": "carbon-x", "name": "Risk", "reasons": { "a": "File safety 15, safetensors and GGUF only, but the documented loading path runs the repository's tokenizer.py through trust_remote_code. Provenance 15, the files are in HuggingFaceBio, which Hugging Face's GitHub repository links, with a checksum on every file. Safety evaluation 10, Hugging Face reports its own dual-use check on sequence editing in the launch post, without numbers or a harness. Agent guidance 5, general cautions only. Licence risk 15, plain Apache 2.0. Security programme 5, Hugging Face's security.txt is a reporting route, and public advisories couldn't be checked.", "b": "File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw." }, "scores": { "a": 65, "b": 55 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Hugging Face (HuggingFaceBio)", "b": "Ricursive Intelligence", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-28", "b": "2026-11-04", "name": "Last release" }, { "a": "no document linked", "b": "not read yet", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Carbon-X scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Ripple-65B Preview leads on agent interface.", "question": "Which is better for AI agents, Carbon-X or Ripple-65B Preview?" } ], "goodFor": [ { "aheadOn": [ "Reach, 90 against 45", "Risk, 65 against 55", "Documentation and upkeep, 72 against 49" ], "also": null, "goodFor": "Agents that need a second opinion on DNA variants and regulatory regions on a 16 to 24 GB machine, without sending sequences to a hosted model.", "slug": "carbon-x", "watchFor": "Not clinically validated and no wet-lab validation reported" }, { "aheadOn": [ "Agent interface, 75 against 35" ], "also": null, "goodFor": "Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.", "slug": "ripple-65b-preview", "watchFor": "No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code" } ], "history": { "carbon-x": [ { "causes": [ "evidence" ], "date": "2026-11-03", "delta": 0, "from": 61, "fromGrade": "C", "to": 61, "toGrade": "C" } ], "ripple-65b-preview": null }, "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-carbon-x.json", "title": "Agents-A1-4B vs Carbon-X", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-carbon-x" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-ripple-65b-preview.json", "title": "Agents-A1-4B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-carbon-x.json", "title": "Apertus v1.5 8B vs Carbon-X", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-carbon-x" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-ripple-65b-preview.json", "title": "Apertus v1.5 8B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-carbon-x.json", "title": "Apodex-1.1-mini vs Carbon-X", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-carbon-x" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-ripple-65b-preview.json", "title": "Apodex-1.1-mini vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-carbon-x.json", "title": "BigBang-v1 vs Carbon-X", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-carbon-x" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-ripple-65b-preview.json", "title": "BigBang-v1 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-cosmos-reason2-2b.json", "title": "Carbon-X vs Cosmos-Reason2-2B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-cosmos-reason2-2b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-darwin-36b-opus.json", "title": "Carbon-X vs Darwin-36B-Opus", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-darwin-36b-opus" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2.json", "title": "Carbon-X vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-1-flash.json", "title": "Carbon-X vs DeepSeek V4.1 Flash", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-1-flash" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-flash-0731.json", "title": "Carbon-X vs DeepSeek-V4-Flash-0731", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-flash-0731" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-diffusiongemma-26b-a4b-it.json", "title": "Carbon-X vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-diffusiongemma-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-12b-it.json", "title": "Carbon-X vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-26b-a4b-it.json", "title": "Carbon-X vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-31b-it.json", "title": "Carbon-X vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e2b-it.json", "title": "Carbon-X vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e4b-it.json", "title": "Carbon-X vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-5-air.json", "title": "Carbon-X vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-7-flash.json", "title": "Carbon-X vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-7-flash" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3.json", "title": "Carbon-X vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash.json", "title": "Carbon-X vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-120b.json", "title": "Carbon-X vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b.json", "title": "Carbon-X vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-granite-4-2-3b.json", "title": "Carbon-X vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-hy3.json", "title": "Carbon-X vs Hy3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling.json", "title": "Carbon-X vs Inkling", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-small.json", "title": "Carbon-X vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Carbon-X vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3.json", "title": "Carbon-X vs Kimi K3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-kolibri-1.json", "title": "Carbon-X vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-kronos.json", "title": "Carbon-X vs Kronos", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-m-1.json", "title": "Carbon-X vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-s-2-1.json", "title": "Carbon-X vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-xs-2-1.json", "title": "Carbon-X vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b.json", "title": "Carbon-X vs LBS-27B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm2-5-2-6b.json", "title": "Carbon-X vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-ling-3-0-tiny.json", "title": "Carbon-X vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Carbon-X vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-minicpm-o-4-5.json", "title": "Carbon-X vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-minicpm5-2b.json", "title": "Carbon-X vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-5.json", "title": "Carbon-X vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-7.json", "title": "Carbon-X vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m3-1-flash.json", "title": "Carbon-X vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-mistral-large-4.json", "title": "Carbon-X vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-muse-glimmer-30b.json", "title": "Carbon-X vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b.json", "title": "Carbon-X vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Carbon-X vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Carbon-X vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-30b-a3b.json", "title": "Carbon-X vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-4b.json", "title": "Carbon-X vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Carbon-X vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-super-120b-a12b.json", "title": "Carbon-X vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-ultra-550b-a55b.json", "title": "Carbon-X vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-occamy-1-0.json", "title": "Carbon-X vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-olmo-3-7b-think.json", "title": "Carbon-X vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-35b-a3b.json", "title": "Carbon-X vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-397b.json", "title": "Carbon-X vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-9b.json", "title": "Carbon-X vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Carbon-X vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-4b-instruct-2507.json", "title": "Carbon-X vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-0-8b.json", "title": "Carbon-X vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-122b-a10b.json", "title": "Carbon-X vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-2b.json", "title": "Carbon-X vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-397b-a17b.json", "title": "Carbon-X vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-4b.json", "title": "Carbon-X vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-9b.json", "title": "Carbon-X vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-27b.json", "title": "Carbon-X vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-35b-a3b.json", "title": "Carbon-X vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-27b.json", "title": "Carbon-X vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-flash-next.json", "title": "Carbon-X vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Carbon-X vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-next.json", "title": "Carbon-X vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Carbon-X vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-2b-instruct.json", "title": "Carbon-X vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Carbon-X vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-32b-instruct.json", "title": "Carbon-X vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-4b-instruct.json", "title": "Carbon-X vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-8b-instruct.json", "title": "Carbon-X vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-qwopus3-8-27b-flash-v2.json", "title": "Carbon-X vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint.json", "title": "Carbon-X vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-smollm3-3b.json", "title": "Carbon-X vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-spark-x2-6-4b.json", "title": "Carbon-X vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-27b.json", "title": "Carbon-X vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Carbon-X vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-thinkingcap-qwen3-8-27b.json", "title": "Carbon-X vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2.json", "title": "Carbon-X vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-ripple-65b-preview.json", "title": "Cosmos-Reason2-2B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-ripple-65b-preview.json", "title": "Darwin-36B-Opus vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ripple-65b-preview.json", "title": "DeepSeek-V3.2 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-ripple-65b-preview.json", "title": "DeepSeek V4.1 Flash vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-ripple-65b-preview.json", "title": "DeepSeek-V4-Flash-0731 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview.json", "title": "DiffusionGemma 26B A4B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ripple-65b-preview.json", "title": "Gemma 4 12B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-ripple-65b-preview.json", "title": "Gemma 4 26B A4B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-ripple-65b-preview.json", "title": "Gemma 4 31B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-ripple-65b-preview.json", "title": "Gemma 4 E2B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-ripple-65b-preview.json", "title": "Gemma 4 E4B IT vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-ripple-65b-preview.json", "title": "GLM-4.5-Air vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-ripple-65b-preview.json", "title": "GLM-4.7-Flash vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview.json", "title": "GLM-5.3-Flash vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview.json", "title": "GLM-5.3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview.json", "title": "gpt-oss-120b vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview.json", "title": "gpt-oss-20b vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ripple-65b-preview.json", "title": "Granite 4.2 3B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview.json", "title": "Hy3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-ripple-65b-preview.json", "title": "Inkling-Small vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview.json", "title": "Inkling vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview.json", "title": "Kimi K3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-ripple-65b-preview.json", "title": "Kolibri-1 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-ripple-65b-preview.json", "title": "Kronos vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/kronos-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-ripple-65b-preview.json", "title": "Laguna M.1 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-ripple-65b-preview.json", "title": "Laguna S 2.1 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-ripple-65b-preview.json", "title": "Laguna XS 2.1 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-ripple-65b-preview.json", "title": "LBS-27B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-ripple-65b-preview.json", "title": "LFM2.5-2.6B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-ripple-65b-preview.json", "title": "Ling-3.0-tiny vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview.json", "title": "MiMo-V2.6 Distill Qwen 9B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ripple-65b-preview.json", "title": "MiniCPM-o 4.5 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-ripple-65b-preview.json", "title": "MiniCPM5-2B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-ripple-65b-preview.json", "title": "MiniMax-M2.5 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-ripple-65b-preview.json", "title": "MiniMax-M2.7 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-ripple-65b-preview.json", "title": "MiniMax-M3.1-Flash vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/mistral-large-4-vs-ripple-65b-preview.json", "title": "Mistral Large 4 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/mistral-large-4-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-ripple-65b-preview.json", "title": "Muse Glimmer 30B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ripple-65b-preview.json", "title": "Nanbeige4.3-33B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ripple-65b-preview.json", "title": "NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-ripple-65b-preview.json", "title": "Nemotron 3.5 Lightning 30B A3B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-ripple-65b-preview.json", "title": "Nemotron 3 Nano 30B A3B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-ripple-65b-preview.json", "title": "Nemotron 3 Nano 4B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-ripple-65b-preview.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-ripple-65b-preview.json", "title": "Nemotron 3 Super 120B A12B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-ripple-65b-preview.json", "title": "Nemotron 3 Ultra 550B A55B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/occamy-1-0-vs-ripple-65b-preview.json", "title": "occamy-1.0 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/occamy-1-0-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview.json", "title": "Olmo 3 7B Think vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-ripple-65b-preview.json", "title": "Ornith-1.5-35B-A3B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-ripple-65b-preview.json", "title": "Ornith-1.5-397B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-ripple-65b-preview.json", "title": "Ornith-1.5-9B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-ripple-65b-preview.json", "title": "Qwen3-30B-A3B-Instruct-2507 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-ripple-65b-preview.json", "title": "Qwen3-4B-Instruct-2507 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-ripple-65b-preview.json", "title": "Qwen3.5-0.8B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-ripple-65b-preview.json", "title": "Qwen3.5-122B-A10B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview.json", "title": "Qwen3.5-2B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-ripple-65b-preview.json", "title": "Qwen3.5-397B-A17B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-ripple-65b-preview.json", "title": "Qwen3.5-4B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-ripple-65b-preview.json", "title": "Qwen3.5-9B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-ripple-65b-preview.json", "title": "Qwen3.6-27B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-ripple-65b-preview.json", "title": "Qwen3.6-35B-A3B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-ripple-65b-preview.json", "title": "Qwen3.8-27B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-ripple-65b-preview.json", "title": "Qwen3.8-Flash-Next vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-Coder-30B-A3B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-ripple-65b-preview.json", "title": "Qwen3-Coder-Next vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-Omni-30B-A3B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-VL-2B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-VL-30B-A3B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-VL-32B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-VL-4B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-ripple-65b-preview.json", "title": "Qwen3-VL-8B-Instruct vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-ripple-65b-preview.json", "title": "Qwopus3.8-27B-Flash-V2 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-ripple-65b-preview.json", "title": "Recursive Flint vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-smollm3-3b.json", "title": "Ripple-65B Preview vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-spark-x2-6-4b.json", "title": "Ripple-65B Preview vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-27b.json", "title": "Ripple-65B Preview vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Ripple-65B Preview vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-thinkingcap-qwen3-8-27b.json", "title": "Ripple-65B Preview vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-unlimited-ocr-2.json", "title": "Ripple-65B Preview vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/ripple-65b-preview-vs-unlimited-ocr-2" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 45, "carbon-x": 90, "edge": "carbon-x", "key": "reach", "name": "Reach", "ripple-65b-preview": 45, "weight": 25 }, { "by": 10, "carbon-x": 65, "edge": "carbon-x", "key": "risk", "name": "Risk", "ripple-65b-preview": 55, "weight": 20 }, { "by": 40, "carbon-x": 35, "edge": "ripple-65b-preview", "key": "interface", "name": "Agent interface", "ripple-65b-preview": 75, "weight": 10 }, { "by": 23, "carbon-x": 72, "edge": "carbon-x", "key": "upkeep", "name": "Documentation and upkeep", "ripple-65b-preview": 49, "weight": 10 } ], "summary": "Carbon-X scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Ripple-65B Preview leads on agent interface. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "carbon-x": "A DNA specialist cousin that another agent calls for variant-effect and sequence questions, with DNA kept on the machine. Hugging Face's Q4_K_M GGUF needs about 12 GB and Q8_0 about 19 GB, on llama.cpp b11742 or later. It isn't clinically validated, isn't trained for tool calls or reasoning, and its Python tokenizer runs repository code.", "ripple-65b-preview": "A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview", "json": "https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.min.md" }, "markdown": "Carbon-X scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Ripple-65B Preview leads on agent interface. Both do open-weight models you run yourself.\n\n- Carbon-X: grade C, 61/100, rank #42 of 121 open-weight models. Markdown https://www.anchorterminal.com/tools/carbon-x.md · JSON https://www.anchorterminal.com/api/v1/tools/carbon-x.json\n- Ripple-65B Preview: grade D, 53.3/100, rank #103 of 121 open-weight models. Markdown https://www.anchorterminal.com/tools/ripple-65b-preview.md · JSON https://www.anchorterminal.com/api/v1/tools/ripple-65b-preview.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 3674 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Carbon-X (C)\n\nGood for: Agents that need a second opinion on DNA variants and regulatory regions on a 16 to 24 GB machine, without sending sequences to a hosted model.\n\nAhead on:\n- Reach, 90 against 45\n- Risk, 65 against 55\n- Documentation and upkeep, 72 against 49\n\nWatch for: Not clinically validated and no wet-lab validation reported\n\n### Ripple-65B Preview (D)\n\nGood for: Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it.\n\nAhead on:\n- Agent interface, 75 against 35\n\nWatch for: No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code\n\n\n## Why the edge\n\n### Reach: Carbon-X +45\n\n- Carbon-X (90): Memory 30, the publisher's Q4_K_M GGUF is 9.6 GB, or 11.6 GB with a fifth added. Runtimes 20, released llama.cpp (from b11742, which added the DNA tokenizer), vLLM, SGLang and Transformers all run it, with no Ollama or LM Studio entry. Builds 15, Hugging Face publishes GGUFs at four precisions. Terms 15, Apache 2.0 on the model and on its Qwen3-14B base. Download 10, nothing is gated. Hosted 0, no inference provider or Hugging Face API serves it.\n- Ripple-65B Preview (45): Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.\n\n### Agent interface: Ripple-65B Preview +40\n\n- Carbon-X (35): Chat template 20, a Jinja file in the repository. Tool-calling format 10, only the inherited template shows the format and no parser is named. Trained tool calling 0, nothing says it was trained to call tools. Structured output 0, not documented. Reasoning control 0, thinking can be switched off but was never trained, and the card asks you to keep it off. Context 5, 40,960 tokens from the base, though Hugging Face trained at 8,192 and under 16K. Most of what the card documents for agents is Carbon-X as a tool another model calls, which this checklist doesn't read.\n- Ripple-65B Preview (75): Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M.\n\n### Documentation and upkeep: Carbon-X +23\n\n- Carbon-X (72): Model card 17, everything but a knowledge cut-off. Training data 15, the mid-training sources and shares are listed, the instruction and fine-tuning data aren't named, and there's no cut-off. Last change 20, 28 October 2026, when config.json, generation_config.json, tokenizer_config.json and tokenizer.py were fixed. Responsiveness 10, organisation members replied to 2 of the 4 questions so far. Version policy 5, a first release whose history was squashed without a note. File health 5, the card now sends llama.cpp users to the publisher's GGUF repository, but the tokenizer config's 131,072 still contradicts the card's 40,960. 17 + 15 + 20 + 10 + 5 + 5 = 72.\n- Ripple-65B Preview (49): Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M.\n\n### Risk: Carbon-X +10\n\n- Carbon-X (65): File safety 15, safetensors and GGUF only, but the documented loading path runs the repository's tokenizer.py through trust_remote_code. Provenance 15, the files are in HuggingFaceBio, which Hugging Face's GitHub repository links, with a checksum on every file. Safety evaluation 10, Hugging Face reports its own dual-use check on sequence editing in the launch post, without numbers or a harness. Agent guidance 5, general cautions only. Licence risk 15, plain Apache 2.0. Security programme 5, Hugging Face's security.txt is a reporting route, and public advisories couldn't be checked.\n- Ripple-65B Preview (55): File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.\n\n## Score by category\n\n| Category | Weight | Carbon-X | Ripple-65B Preview | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 90 | 45 | Carbon-X +45 |\n| Risk | 20% (20 this run) | 65 | 55 | Carbon-X +10 |\n| Agent interface | 10% (10 this run) | 35 | 75 | Ripple-65B Preview +40 |\n| Documentation and upkeep | 10% (10 this run) | 72 | 49 | Carbon-X +23 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61 · C** | **53.3 · D** | |\n\n## Facts side by side\n\n| Fact | Carbon-X | Ripple-65B Preview |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Hugging Face (HuggingFaceBio) | Ricursive Intelligence |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-28 | 2026-11-04 |\n| Terms last updated | no document linked | not read yet |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 3/5 (4) | none |\n\n## How the scores have moved\n\n### Carbon-X\n\n- no change on 3 November 2026: new evidence\n\n### Ripple-65B Preview\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Carbon-X.** A DNA specialist cousin that another agent calls for variant-effect and sequence questions, with DNA kept on the machine. Hugging Face's Q4_K_M GGUF needs about 12 GB and Q8_0 about 19 GB, on llama.cpp b11742 or later. It isn't clinically validated, isn't trained for tool calls or reasoning, and its Python tokenizer runs repository code.\n\n**Ripple-65B Preview.** A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.\n\n## Before you call either\n\n### Carbon-X\n\n1. Quickest start is `llama-server -hf HuggingFaceBio/Carbon-X-GGUF:Q8_0 -ngl 99 -c 40960 --jinja --chat-template-kwargs '{\"enable_thinking\": false}' --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0`, on llama.cpp b11742 or later\n2. With vLLM or Transformers pass trust_remote_code, and expect the tokenizer to fetch Qwen/Qwen3-4B-Base at a pinned revision on first load\n3. Keep enable_thinking false and the card's sampling (temperature 0.6, top_p 0.95, top_k 20), the settings every reported result used\n4. Keep DNA in files and pass sequences by name, compute positions and base changes in code and send them as context, the card says the model miscounts long sequences\n5. Only A, C, G and T form 6-mers, so filter N and other IUPAC codes first or they become a single oov token\n6. Strip the dna tags from answers if you need bare sequence, llama.cpp keeps them in the text\n7. Cap max_tokens for next-base questions, long DNA generation is slow and degrades\n\n### Ripple-65B Preview\n\n1. Run Ricursive's launcher from inference/server with `uv run --script serve.py` on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default\n2. The launcher turns on `--reasoning-parser ripple` and `--tool-call-parser ripple`; without them tool calls come back as raw text inside tool_call tags\n3. For `tool_choice: \"required\"` set `strict: true` and `additionalProperties: false` on each function, which the README says stopped extra argument fields\n4. Leave room in `max_tokens` for reasoning as well as the answer, since thinking is always on\n5. Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support\n\n## Questions\n\n### Which is better for AI agents, Carbon-X or Ripple-65B Preview?\n\nCarbon-X scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories. Ripple-65B Preview leads on agent interface.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.json, and with the fewest tokens: https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"carbon-x\", \"b\": \"ripple-65b-preview\"}`. From a terminal: `anchor compare carbon-x ripple-65b-preview`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/carbon-x.json and https://www.anchorterminal.com/api/v1/tools/ripple-65b-preview.json\n\n## Other comparisons with Carbon-X or Ripple-65B Preview\n\n- [Agents-A1-4B vs Carbon-X](https://www.anchorterminal.com/compare/agents-a1-4b-vs-carbon-x.md)\n- [Agents-A1-4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/agents-a1-4b-vs-ripple-65b-preview.md)\n- [Apertus v1.5 8B vs Carbon-X](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-carbon-x.md)\n- [Apertus v1.5 8B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-ripple-65b-preview.md)\n- [Apodex-1.1-mini vs Carbon-X](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-carbon-x.md)\n- [Apodex-1.1-mini vs Ripple-65B Preview](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-ripple-65b-preview.md)\n- [BigBang-v1 vs Carbon-X](https://www.anchorterminal.com/compare/bigbang-v1-vs-carbon-x.md)\n- [BigBang-v1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/bigbang-v1-vs-ripple-65b-preview.md)\n- [Carbon-X vs Cosmos-Reason2-2B](https://www.anchorterminal.com/compare/carbon-x-vs-cosmos-reason2-2b.md)\n- [Carbon-X vs Darwin-36B-Opus](https://www.anchorterminal.com/compare/carbon-x-vs-darwin-36b-opus.md)\n- [Carbon-X vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2.md)\n- [Carbon-X vs DeepSeek V4.1 Flash](https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-1-flash.md)\n- [Carbon-X vs DeepSeek-V4-Flash-0731](https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v4-flash-0731.md)\n- [Carbon-X vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/carbon-x-vs-diffusiongemma-26b-a4b-it.md)\n- [Carbon-X vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-12b-it.md)\n- [Carbon-X vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-26b-a4b-it.md)\n- [Carbon-X vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-31b-it.md)\n- [Carbon-X vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e2b-it.md)\n- [Carbon-X vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/carbon-x-vs-gemma-4-e4b-it.md)\n- [Carbon-X vs GLM-4.5-Air](https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-5-air.md)\n- [Carbon-X vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/carbon-x-vs-glm-4-7-flash.md)\n- [Carbon-X vs GLM-5.3](https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3.md)\n- [Carbon-X vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash.md)\n- [Carbon-X vs gpt-oss-120b](https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-120b.md)\n- [Carbon-X vs gpt-oss-20b](https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b.md)\n- [Carbon-X vs Granite 4.2 3B](https://www.anchorterminal.com/compare/carbon-x-vs-granite-4-2-3b.md)\n- [Carbon-X vs Hy3](https://www.anchorterminal.com/compare/carbon-x-vs-hy3.md)\n- [Carbon-X vs Inkling](https://www.anchorterminal.com/compare/carbon-x-vs-inkling.md)\n- [Carbon-X vs Inkling-Small](https://www.anchorterminal.com/compare/carbon-x-vs-inkling-small.md)\n- [Carbon-X vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/carbon-x-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Carbon-X vs Kimi K3](https://www.anchorterminal.com/compare/carbon-x-vs-kimi-k3.md)\n- [Carbon-X vs Kolibri-1](https://www.anchorterminal.com/compare/carbon-x-vs-kolibri-1.md)\n- [Carbon-X vs Kronos](https://www.anchorterminal.com/compare/carbon-x-vs-kronos.md)\n- [Carbon-X vs Laguna M.1](https://www.anchorterminal.com/compare/carbon-x-vs-laguna-m-1.md)\n- [Carbon-X vs Laguna S 2.1](https://www.anchorterminal.com/compare/carbon-x-vs-laguna-s-2-1.md)\n- [Carbon-X vs Laguna XS 2.1](https://www.anchorterminal.com/compare/carbon-x-vs-laguna-xs-2-1.md)\n- [Carbon-X vs LBS-27B](https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b.md)\n- [Carbon-X vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/carbon-x-vs-lfm2-5-2-6b.md)\n- [Carbon-X vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/carbon-x-vs-ling-3-0-tiny.md)\n- [Carbon-X vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/carbon-x-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Carbon-X vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/carbon-x-vs-minicpm-o-4-5.md)\n- [Carbon-X vs MiniCPM5-2B](https://www.anchorterminal.com/compare/carbon-x-vs-minicpm5-2b.md)\n- [Carbon-X vs MiniMax-M2.5](https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-5.md)\n- [Carbon-X vs MiniMax-M2.7](https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m2-7.md)\n- [Carbon-X vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/carbon-x-vs-minimax-m3-1-flash.md)\n- [Carbon-X vs Mistral Large 4](https://www.anchorterminal.com/compare/carbon-x-vs-mistral-large-4.md)\n- [Carbon-X vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/carbon-x-vs-muse-glimmer-30b.md)\n- [Carbon-X vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b.md)\n- [Carbon-X vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Carbon-X vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Carbon-X vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-30b-a3b.md)\n- [Carbon-X vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-4b.md)\n- [Carbon-X vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Carbon-X vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-super-120b-a12b.md)\n- [Carbon-X vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/carbon-x-vs-nemotron-3-ultra-550b-a55b.md)\n- [Carbon-X vs occamy-1.0](https://www.anchorterminal.com/compare/carbon-x-vs-occamy-1-0.md)\n- [Carbon-X vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/carbon-x-vs-olmo-3-7b-think.md)\n- [Carbon-X vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-35b-a3b.md)\n- [Carbon-X vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-397b.md)\n- [Carbon-X vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/carbon-x-vs-ornith-1-5-9b.md)\n- [Carbon-X vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Carbon-X vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-4b-instruct-2507.md)\n- [Carbon-X vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-0-8b.md)\n- [Carbon-X vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-122b-a10b.md)\n- [Carbon-X vs Qwen3.5-2B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-2b.md)\n- [Carbon-X vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-397b-a17b.md)\n- [Carbon-X vs Qwen3.5-4B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-4b.md)\n- [Carbon-X vs Qwen3.5-9B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-5-9b.md)\n- [Carbon-X vs Qwen3.6-27B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-27b.md)\n- [Carbon-X vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-6-35b-a3b.md)\n- [Carbon-X vs Qwen3.8-27B](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-27b.md)\n- [Carbon-X vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-8-flash-next.md)\n- [Carbon-X vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Carbon-X vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-coder-next.md)\n- [Carbon-X vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Carbon-X vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-2b-instruct.md)\n- [Carbon-X vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Carbon-X vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-32b-instruct.md)\n- [Carbon-X vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-4b-instruct.md)\n- [Carbon-X vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/carbon-x-vs-qwen3-vl-8b-instruct.md)\n- [Carbon-X vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/carbon-x-vs-qwopus3-8-27b-flash-v2.md)\n- [Carbon-X vs Recursive Flint](https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint.md)\n- [Carbon-X vs SmolLM3-3B](https://www.anchorterminal.com/compare/carbon-x-vs-smollm3-3b.md)\n- [Carbon-X vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/carbon-x-vs-spark-x2-6-4b.md)\n- [Carbon-X vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-27b.md)\n- [Carbon-X vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/carbon-x-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Carbon-X vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/carbon-x-vs-thinkingcap-qwen3-8-27b.md)\n- [Carbon-X vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2.md)\n- [Cosmos-Reason2-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-ripple-65b-preview.md)\n- [Darwin-36B-Opus vs Ripple-65B Preview](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-ripple-65b-preview.md)\n- [DeepSeek-V3.2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ripple-65b-preview.md)\n- [DeepSeek V4.1 Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-ripple-65b-preview.md)\n- [DeepSeek-V4-Flash-0731 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-ripple-65b-preview.md)\n- [DiffusionGemma 26B A4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-ripple-65b-preview.md)\n- [Gemma 4 12B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-ripple-65b-preview.md)\n- [Gemma 4 26B A4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-ripple-65b-preview.md)\n- [Gemma 4 31B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-ripple-65b-preview.md)\n- [Gemma 4 E2B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-ripple-65b-preview.md)\n- [Gemma 4 E4B IT vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-ripple-65b-preview.md)\n- [GLM-4.5-Air vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-4-5-air-vs-ripple-65b-preview.md)\n- [GLM-4.7-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-ripple-65b-preview.md)\n- [GLM-5.3-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview.md)\n- [GLM-5.3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview.md)\n- [gpt-oss-120b vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-ripple-65b-preview.md)\n- [gpt-oss-20b vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview.md)\n- [Granite 4.2 3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-ripple-65b-preview.md)\n- [Hy3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview.md)\n- [Inkling-Small vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-small-vs-ripple-65b-preview.md)\n- [Inkling vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-vs-ripple-65b-preview.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ripple-65B Preview](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ripple-65b-preview.md)\n- [Kimi K3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kimi-k3-vs-ripple-65b-preview.md)\n- [Kolibri-1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kolibri-1-vs-ripple-65b-preview.md)\n- [Kronos vs Ripple-65B Preview](https://www.anchorterminal.com/compare/kronos-vs-ripple-65b-preview.md)\n- [Laguna M.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-m-1-vs-ripple-65b-preview.md)\n- [Laguna S 2.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-ripple-65b-preview.md)\n- [Laguna XS 2.1 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-ripple-65b-preview.md)\n- [LBS-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lbs-27b-vs-ripple-65b-preview.md)\n- [LFM2.5-2.6B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-ripple-65b-preview.md)\n- [Ling-3.0-tiny vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-ripple-65b-preview.md)\n- [MiMo-V2.6 Distill Qwen 9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview.md)\n- [MiniCPM-o 4.5 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-ripple-65b-preview.md)\n- [MiniCPM5-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minicpm5-2b-vs-ripple-65b-preview.md)\n- [MiniMax-M2.5 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m2-5-vs-ripple-65b-preview.md)\n- [MiniMax-M2.7 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m2-7-vs-ripple-65b-preview.md)\n- [MiniMax-M3.1-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-ripple-65b-preview.md)\n- [Mistral Large 4 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/mistral-large-4-vs-ripple-65b-preview.md)\n- [Muse Glimmer 30B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-ripple-65b-preview.md)\n- [Nanbeige4.3-33B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ripple-65b-preview.md)\n- [NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-ripple-65b-preview.md)\n- [Nemotron 3.5 Lightning 30B A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-ripple-65b-preview.md)\n- [Nemotron 3 Nano 30B A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-ripple-65b-preview.md)\n- [Nemotron 3 Nano 4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-ripple-65b-preview.md)\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-ripple-65b-preview.md)\n- [Nemotron 3 Super 120B A12B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-ripple-65b-preview.md)\n- [Nemotron 3 Ultra 550B A55B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-ripple-65b-preview.md)\n- [occamy-1.0 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/occamy-1-0-vs-ripple-65b-preview.md)\n- [Olmo 3 7B Think vs Ripple-65B Preview](https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-ripple-65b-preview.md)\n- [Ornith-1.5-35B-A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-ripple-65b-preview.md)\n- [Ornith-1.5-397B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-ripple-65b-preview.md)\n- [Ornith-1.5-9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-ripple-65b-preview.md)\n- [Qwen3-30B-A3B-Instruct-2507 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-ripple-65b-preview.md)\n- [Qwen3-4B-Instruct-2507 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-ripple-65b-preview.md)\n- [Qwen3.5-0.8B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-ripple-65b-preview.md)\n- [Qwen3.5-122B-A10B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-ripple-65b-preview.md)\n- [Qwen3.5-2B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-2b-vs-ripple-65b-preview.md)\n- [Qwen3.5-397B-A17B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-ripple-65b-preview.md)\n- [Qwen3.5-4B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-4b-vs-ripple-65b-preview.md)\n- [Qwen3.5-9B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-5-9b-vs-ripple-65b-preview.md)\n- [Qwen3.6-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-6-27b-vs-ripple-65b-preview.md)\n- [Qwen3.6-35B-A3B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-ripple-65b-preview.md)\n- [Qwen3.8-27B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-8-27b-vs-ripple-65b-preview.md)\n- [Qwen3.8-Flash-Next vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-ripple-65b-preview.md)\n- [Qwen3-Coder-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-Coder-Next vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-coder-next-vs-ripple-65b-preview.md)\n- [Qwen3-Omni-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-VL-2B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-VL-30B-A3B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-VL-32B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-VL-4B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-ripple-65b-preview.md)\n- [Qwen3-VL-8B-Instruct vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-ripple-65b-preview.md)\n- [Qwopus3.8-27B-Flash-V2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-ripple-65b-preview.md)\n- [Recursive Flint vs Ripple-65B Preview](https://www.anchorterminal.com/compare/recursive-flint-vs-ripple-65b-preview.md)\n- [Ripple-65B Preview vs SmolLM3-3B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-smollm3-3b.md)\n- [Ripple-65B Preview vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-spark-x2-6-4b.md)\n- [Ripple-65B Preview vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-27b.md)\n- [Ripple-65B Preview vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Ripple-65B Preview vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-thinkingcap-qwen3-8-27b.md)\n- [Ripple-65B Preview vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ripple-65b-preview-vs-unlimited-ocr-2.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-05", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Carbon-X vs Ripple-65B Preview", "url": "" } ], "description": "Carbon-X scores 61 (C) to Ripple-65B Preview's 53.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Carbon-X C 61", "Ripple-65B Preview D 53.3", "scores" ], "h1": "Carbon-X vs Ripple-65B Preview", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/carbon-x-vs-ripple-65b-preview", "published": "2026-10-01", "section": "tools", "title": "Carbon-X vs Ripple-65B Preview for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-04", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-ripple-65b-preview" }, "tokens": { "markdown": 7750, "slim": 1580 }, "version": 1 }