{ "data": { "a": { "slug": "drex-max-v1", "name": "Drex Max v1", "vendor": "Nace AI, Inc. (Nace.AI)", "vendorUrl": "https://www.nace.ai", "kind": "weights", "category": "decision-models", "summary": "Drex Max v1 is Nace.AI's open-weight 27B decision model, a fine-tune of Qwen3.8-27B that takes text, JSON and images with typed questions and returns a probability for every option without generating text.", "url": "https://www.anchorterminal.com/tools/drex-max-v1", "markdownUrl": "https://www.anchorterminal.com/tools/drex-max-v1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/drex-max-v1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/drex-max-v1.json", "repo": "https://huggingface.co/nace-ai/drex-max-v1", "license": "Nace.AI Open RAIL-M License (modified), version 1.0, October 2026, in the repository's LICENSE. Not an open-source licence. Use is free only for individuals and organisations under $1 million in revenue in the prior 12 months and under $1 million in total funding (personal and research use excepted), never by anyone with a product that competes with Nace's, decision models included, and under use restrictions that bind the model, its derivatives and its outputs. Built on Qwen/Qwen3.8-27B (Apache-2.0), whose licence text isn't carried in the repository", "transports": [], "packages": [ { "registry": "huggingface", "name": "nace-ai/drex-max-v1" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository and both quantised builds are not gated (checked 2026-10-30). The licence says downloading binds you to its terms. Nace's hosted API for the same model needs a nace_sk_ key.", "pricing": "free", "pricingNotes": "Free to download. Commercial use by anyone above $1 million in revenue or funding, or with a product that competes with Nace's, needs a separate licence from Nace.AI. Running it costs the hardware, from 14.5 GB of files (affine 4-bit, text only) to 52.2 GB (BF16). Nace's API serves it as drex-max at $0.03 per million input tokens, with output not billed (checked 2026-10-30).", "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 2026-10-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/nace-ai/drex-decision-models/blob/main/models/drex-max-v1", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "full-fine-tune", "calibrated-probabilities", "vision", "open-rail-m", "safetensors", "gguf", "self-hosted", "apple-silicon" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 55.5, "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": 1243, "categoryRank": 17, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 80, "reach": 65, "risk": 45, "upkeep": 41 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-30" }, "negative": -2, "negativeNotes": [ "19 October 2026, still on the page on 30 October. Nace's blog says Drex Max is 'First among decision models on the public Decision Index 0.4.0'. The index (multimodalart/jev-decision-index, data generated 29 October 2026) ranks it 23rd of 247 by public score at 67.52, behind mammoth-1 (75.34) among others, and 24th of 247 by the Full score it ranks by (66.6). Its data of 16 October, before the blog, already had StartLux-Decision v1.1 27B (72.88), KnowLine 35B-A3B Gen1 (69.49) and Perplexity Decider v1.2 (67.74) above 67.52 on the public score. The Vision board ranks it 11th of 62. Sources: https://www.nace.ai/blog/introducing-drex-max and https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json (-2)" ], "verdict": "A 27B cousin for typed decisions over text and screenshots, several questions per request with a probability for each option. Images need an NVIDIA GPU and Nace's loader; on Apple silicon only the text backbone runs, from 24 GB. The licence isn't open source, with free commercial use only under $1 million in revenue and funding.", "bestFor": "Agents that want self-hosted routing, triage or screen decisions with probabilities, on a CUDA GPU with 48 GB or more for images or a 24 GB Mac for text, where the Open RAIL-M terms fit.", "strengths": [ "Probabilities for choice, yes or no and score questions over text, JSON and images, with nothing generated", "Full score 66.6 on the Jev Decision Index 0.4.1, 24th of 247, and 11th of 62 on its Vision board, from the index's private tests", "Nace publishes a Q8_0 GGUF and an affine 4-bit build, the smaller at 14.5 GB for Macs with 24 GB", "Not gated, and Nace's own API serves it as drex-max at $0.03 per million input tokens", "262,144-token window in config.json and the docs, with a 16,384-token default you can raise" ], "weaknesses": [ "The licence bars commercial use above $1 million in revenue or funding and by anyone with a competing product, and restricts the outputs too", "Every path that runs it as trained is Nace's own code or forks. Stock llama.cpp, Ollama, vLLM and Transformers run it causally", "Images need the Python loader on a CUDA GPU; the GGUF and 4-bit builds read text only", "The card gives no limitations, languages, cut-off or training data, and dropped its Qwen3.8-27B base on 30 October 2026", "No safety results and no prompt-injection guidance on the card" ], "agentNotes": [ "Clone github.com/nace-ai/drex-decision-models, download nace-ai/drex-max-v1 and run `python -m drex_max --model weights/drex-max-v1 --request examples/request.json` on an NVIDIA GPU", "Plan for about 49 GB of GPU memory in BF16, or about 26 GB with --8bit on CUDA, before any long context", "Don't load it with stock Transformers, vLLM or llama.cpp. Its full-attention layers must run non-causally with readout.safetensors applied, which only Nace's loader and forks do", "On a Mac with 24 GB or more, run `kapitsa-systemone --model ./drex-max-v1-affine-q4 --port 8000 --context 2048` for text-only decisions at POST /v1/systemone", "Raise the 16,384-token default with DREX_MAX_CONTEXT=N or --max-length N, up to 262,144, and expect more memory", "Check the licence first. Above $1 million in revenue or funding, or with a competing product, you need Nace's commercial licence" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.5 } ], "editorialScores": { "interface": 80, "reach": 65, "risk": 45, "upkeep": 41 }, "provenanceScore": 58, "checked": { "categories": { "interface": "2026-10-30", "reach": "2026-10-30", "risk": "2026-10-30", "upkeep": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://github.com/nace-ai/drex-decision-models \u0026\u0026 cd drex-decision-models\nhf download nace-ai/drex-max-v1 --local-dir weights/drex-max-v1\npip install -r models/drex-max-v1/requirements.txt\npython -m drex_max --model weights/drex-max-v1 --request examples/request.json # NVIDIA GPU, Python 3.12+; add --8bit for about 26 GB", "http": "kapitsa-systemone --model ./drex-max-v1-affine-q4 --port 8000 --context 2048 # Apple silicon, text only, after brew install nace-ai/tap/kapitsa and hf download nace-ai/drex-max-v1-affine-q4" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/drex-max-v1" }, "sameModel": [ "nace-drex" ], "weights": { "trainedBy": "Nace.AI, on Alibaba's Qwen3.8-27B", "builtOn": "Qwen/Qwen3.8-27B (full fine-tune with a 255-way readout head, Apache-2.0)", "params": "27B", "context": 262144, "goodFor": "Typed decisions with a probability per option over text, JSON and images, such as routing, triage and the next click in a computer-use loop, several questions per request, with no text generated.", "runtimes": [ "Transformers (Nace's loader)", "llama.cpp (Nace fork, text only)", "Ollama (Nace fork, text only)", "Kapitsa (Nace, text only)", "MLX (Nace script, text only)" ], "builds": [ { "name": "drex-max-v1-affine-q4", "url": "https://huggingface.co/nace-ai/drex-max-v1-affine-q4", "who": "publisher", "precision": "affine 4-bit, group 64", "sizeGB": 14.5, "memoryGB": 24, "format": "safetensors (MLX)", "runsOn": [ "Kapitsa 0.2.25+", "MLX (drex_max_mlx.py)" ], "note": "model.safetensors (14.45 GB), pointer.bin (the readout, raw KPS1 format), tokenizer and configs, 14.47 GB summed from the Hub's file list. 14.47 × 1.2 = 17.4 GB. Text only, added on 30 October 2026" }, { "name": "drex-max-v1-Q8_0", "url": "https://huggingface.co/nace-ai/drex-max-v1-Q8_0", "who": "publisher", "precision": "q8_0", "sizeGB": 27.3, "memoryGB": 48, "format": "gguf", "runsOn": [ "llama.cpp (Nace fork, branch drex-max-v1)", "Ollama (Nace fork, branch drex-max-v1)", "Kapitsa" ], "note": "drex-max-v1-Q8_0.gguf, 27,250,125,216 bytes, with causal attention off and the readout as pointer tensors. 27.25 × 1.2 = 32.7 GB, and the card says it needs 48 GB. Text only" }, { "name": "drex-max-v1", "url": "https://huggingface.co/nace-ai/drex-max-v1", "who": "publisher", "precision": "bf16", "sizeGB": 52.2, "memoryGB": 64, "format": "safetensors", "runsOn": [ "Transformers 5.17.0 with Nace's loader (CUDA)" ], "note": "11 shards (52.17 GB), readout.safetensors (2.6 MB), tokenizer, configs, images and loader code, 52.19 GB summed from the Hub's file list. 52.19 × 1.2 = 62.6 GB. The only build that reads images. Loading the backbone in 8-bit on CUDA takes about 26 GB, per the card" } ], "run": "python -m drex_max --model weights/drex-max-v1 --request examples/request.json", "runBuild": "drex-max-v1", "checked": "2026-10-30", "minMemoryGB": 24 }, "family": { "lab": "Nace.AI", "family": "Drex", "url": "https://www.anchorterminal.com/open-weights/#nace", "others": [ { "name": "Drex v1.5", "url": "https://huggingface.co/nace-ai/drex-v1.5", "params": "9B (8,953,803,264 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/nace-drex" }, { "name": "Drex DLM", "url": "https://huggingface.co/nace-ai/drex-dlm", "params": "8B (8,190,735,360 by the Hub's safetensors count)" }, { "name": "Drex v2.0", "url": "https://huggingface.co/nace-ai/drex-v2.0", "params": "35B-A3B (35,107,181,936 by the Hub's safetensors count)" } ], "olderCount": 1 }, "area": "models", "provenance": { "legalEntity": "Nace AI, Inc.", "domain": "nace.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "valid", "checked": "2026-10-30", "notes": [ "The legal entity is from the nace-drex listing's check of Nace's terms on 10 October 2026.", "The nace-ai Hugging Face organisation is unverified, with 19 members, among them the two accounts that committed to this repository. nace.ai/drex links to huggingface.co/nace-ai and to github.com/nace-ai, whose drex-decision-models repository links these weights.", "Nothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.", "security.txt at www.nace.ai is valid until 30 October 2027 and points to trust.nace.ai for contact and policy." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/drex-max-v1.json" }, "answer": "joey-1 scores 57.1 (C) on agent readiness against Drex Max v1's 55.5 (C), and leads in 2 of 4 scored categories. Drex Max v1 leads on reach and agent interface.", "b": { "slug": "joey-1", "name": "joey-1", "vendor": "Baseten", "vendorUrl": "https://labs.baseten.co", "kind": "weights", "category": "decision-models", "summary": "joey-1 is Base Labs' open-weight 2B decision model, a full fine-tune of Qwen3.5-2B that takes text and images and returns a probability for every option of typed questions about a state in one prefill. Base Labs is Baseten's research lab.", "url": "https://www.anchorterminal.com/tools/joey-1", "markdownUrl": "https://www.anchorterminal.com/tools/joey-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/joey-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/joey-1.json", "repo": "https://huggingface.co/baselabs/joey-1", "license": "MIT, named in the card's metadata (license: mit) since the upload of 27 October 2026, with no LICENSE file. The base Qwen/Qwen3.5-2B is Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "baselabs/joey-1" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-30). Baseten's hosted Model API for the same model needs a Baseten API key.", "pricing": "free", "pricingNotes": "Free to download under the MIT licence the card's metadata names. Running it costs the hardware, 5.47 GB of BF16 files by the Hub's file list. Baseten also serves it on its Model APIs as decision-models/baseten-joey-2b-latest at $0.01 per million input tokens, with cached input and output at $0.00, per its library page (checked 2026-10-30).", "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 2026-10-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://huggingface.co/baselabs/joey-1", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "full-fine-tune", "calibrated-probabilities", "vision", "mit", "safetensors", "self-hosted" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 57.1, "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": 1243, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 70, "reach": 60, "risk": 55, "upkeep": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-30" }, "negative": -2, "negativeNotes": [ "29 October 2026. Baseten's library page says 'On release (October 2026), joey-1 is the top 2B model on the Jev Decision Index 0.4.' The index (edition 0.4.1, joey-1 added 29 October in PR #330) ranks by its Full score and says the public benchmarks don't count. On it joey-1 has 35.91, 149th of 247, below StartLux-Decision v1.1 2B at 40.11 on the same Qwen3.5-2B base. Only the public score (63.30, first of the models under 4B) supports the claim, and the card names that split while the library page doesn't. Sources: https://www.baseten.co/library/joey-1/ and https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json (-2)" ], "verdict": "A very small cousin for routing, triage and guardrail checks, answering several typed questions about one state, with text or images, as probabilities from one prefill. It fits an 8 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are weak results on the Decision Index's new-domain tests and no safety results.", "bestFor": "Agents that want self-hosted, low-cost ticket routing or guardrail checks with probabilities to threshold, on a GPU with 8 GB, and can accept a patched runtime.", "strengths": [ "Probabilities for choice, yes or no and score questions, several per request from one shared prefill, over text and images", "5.5 GB in BF16, so it fits an 8 GB GPU", "Highest public score of every model under 4B on the Jev Decision Index 0.4.1 at 63.30", "The card documents the request, answer fields and a runnable call, and the licence has been MIT since upload", "Not gated, and Baseten's own Model API serves the same model at $0.01 per million input tokens" ], "weaknesses": [ "Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support", "Full score 35.91 on the Decision Index's private tests, 10.2 on new domains, with one test excluded for signs of training overlap", "Trained at 16,384 tokens, and longer requests are refused", "No quantised build, no safety results and no prompt-injection guidance", "No LICENSE file, and the Apache-2.0 base's licence isn't carried" ], "agentNotes": [ "Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with `hf download baselabs/joey-1 --local-dir joey-1 \u0026\u0026 bash joey-1/setup.sh`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit", "Then call `DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\").decide(SystemOneRequest(state=..., questions=...))` from qev, as the card shows", "Don't load it with stock vLLM or Transformers. They ignore the block-bidirectional attention in config.json's modeling_overrides and give probabilities the model wasn't trained for", "Keep each request under 16,384 tokens, the trained length, or the engine refuses it", "Expect weaker answers on domains unlike its training mix, and threshold on the returned probability before acting", "Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-joey-2b-latest with a Baseten key" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.1 } ], "editorialScores": { "interface": 70, "reach": 60, "risk": 55, "upkeep": 54 }, "provenanceScore": 50, "checked": { "categories": { "interface": "2026-10-30", "reach": "2026-10-30", "risk": "2026-10-30", "upkeep": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "hf download baselabs/joey-1 --local-dir joey-1 \u0026\u0026 bash joey-1/setup.sh # clones OneJev at 81ce62f, applies serve.patch, installs the Decision Index kit (CUDA image pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel)\n# then, in Python:\nfrom qev.engine import DecisionEngine\nfrom qev.schema import SystemOneRequest\nengine = DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\")\nresp, _ = engine.decide(SystemOneRequest(state=..., questions={...}))" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/joey-1" }, "sameCompany": [ "baseten", "elephant-1", "mammoth-1" ], "weights": { "trainedBy": "Base Labs (Baseten), on Alibaba's Qwen3.5-2B", "builtOn": "Qwen/Qwen3.5-2B (full fine-tune, Apache-2.0)", "params": "2B", "context": 16384, "goodFor": "Cheap typed decisions with calibrated probabilities over text and images, several choice, yes or no and score questions about one state in one prefill, for routing, triage and guardrails on a small GPU.", "runtimes": [ "OneJev qev (patched)" ], "builds": [ { "name": "joey-1", "url": "https://huggingface.co/baselabs/joey-1", "who": "publisher", "precision": "bf16", "sizeGB": 5.5, "memoryGB": 8, "format": "safetensors", "runsOn": [ "OneJev qev with serve.patch" ], "note": "model.safetensors (5.44 GB), tokenizer, configs, banner and serving bundle, 5.47 GB summed from the Hub's file list. 5.47 × 1.2 = 6.6 GB. No quantised build from Base Labs and no Ollama or LM Studio library entry" } ], "run": "bash setup.sh \u0026\u0026 python -c 'from qev.engine import DecisionEngine; DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\")'", "runBuild": "joey-1", "checked": "2026-10-30", "minMemoryGB": 8 }, "family": { "lab": "Base Labs (Baseten)", "family": "Base Labs decision models (-1)", "url": "https://www.anchorterminal.com/open-weights/#baselabs", "others": [ { "name": "elephant-1", "url": "https://huggingface.co/baselabs/elephant-1", "params": "9B (9,409,813,744 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/elephant-1" }, { "name": "mammoth-1", "url": "https://huggingface.co/baselabs/mammoth-1", "params": "27B (27,356,728,560 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/mammoth-1" } ] }, "area": "models", "provenance": { "legalEntity": "Baseten Labs, Inc.", "domain": "baseten.co", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "Base Labs is Baseten's research lab (labs.baseten.co). The legal entity is from the baseten listing's check of Baseten's terms on 30 September 2026.", "The baselabs Hugging Face organisation is unverified, with nine members, among them the Base Labs report's authors. Baseten's library page and the card link it to Baseten.", "Nothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.", "No changelog. security.txt is recorded as absent from the elephant-1 check of 21 October 2026 and wasn't re-read." ], "score": 50 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/joey-1.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Nace AI, Inc. (Nace.AI)", "b": "Baseten", "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": "Nace.AI Open RAIL-M License (modified), version 1.0, October 2026, in the repository's LICENSE. Not an open-source licence. Use is free only for individuals and organisations under $1 million in revenue in the prior 12 months and under $1 million in total funding (personal and research use excepted), never by anyone with a product that competes with Nace's, decision models included, and under use restrictions that bind the model, its derivatives and its outputs. Built on Qwen/Qwen3.8-27B (Apache-2.0), whose licence text isn't carried in the repository", "b": "MIT, named in the card's metadata (license: mit) since the upload of 27 October 2026, with no LICENSE file. The base Qwen/Qwen3.5-2B is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-10-29", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "joey-1 scores 57.1 (C) on agent readiness against Drex Max v1's 55.5 (C), and leads in 2 of 4 scored categories. Drex Max v1 leads on reach and agent interface.", "question": "Which is better for AI agents, Drex Max v1 or joey-1?" } ], "goodFor": [ { "aheadOn": [ "Reach, 65 against 60", "Agent interface, 80 against 70" ], "also": null, "goodFor": "Agents that want self-hosted routing, triage or screen decisions with probabilities, on a CUDA GPU with 48 GB or more for images or a 24 GB Mac for text, where the Open RAIL-M terms fit.", "slug": "drex-max-v1", "watchFor": "The licence bars commercial use above $1 million in revenue or funding and by anyone with a competing product, and restricts the outputs too" }, { "aheadOn": [ "Risk, 55 against 45", "Documentation and upkeep, 54 against 41" ], "also": null, "goodFor": "Agents that want self-hosted, low-cost ticket routing or guardrail checks with probabilities to threshold, on a GPU with 8 GB, and can accept a patched runtime.", "slug": "joey-1", "watchFor": "Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/drex-max-v1-vs-elephant-1.json", "title": "Drex Max v1 vs elephant-1", "url": "https://www.anchorterminal.com/compare/drex-max-v1-vs-elephant-1" }, { "json": "https://www.anchorterminal.com/compare/drex-max-v1-vs-jev-27b-vl.json", "title": "Drex Max v1 vs JEV-27B-VL", "url": "https://www.anchorterminal.com/compare/drex-max-v1-vs-jev-27b-vl" }, { "json": "https://www.anchorterminal.com/compare/drex-max-v1-vs-mammoth-1.json", "title": "Drex Max v1 vs mammoth-1", "url": "https://www.anchorterminal.com/compare/drex-max-v1-vs-mammoth-1" }, { "json": "https://www.anchorterminal.com/compare/elephant-1-vs-joey-1.json", "title": "elephant-1 vs joey-1", "url": "https://www.anchorterminal.com/compare/elephant-1-vs-joey-1" }, { "json": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.json", "title": "JEV-27B-VL vs joey-1", "url": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1" }, { "json": "https://www.anchorterminal.com/compare/joey-1-vs-mammoth-1.json", "title": "joey-1 vs mammoth-1", "url": "https://www.anchorterminal.com/compare/joey-1-vs-mammoth-1" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 5, "drex-max-v1": 65, "edge": "drex-max-v1", "joey-1": 60, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 10, "drex-max-v1": 45, "edge": "joey-1", "joey-1": 55, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 10, "drex-max-v1": 80, "edge": "drex-max-v1", "joey-1": 70, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 13, "drex-max-v1": 41, "edge": "joey-1", "joey-1": 54, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "joey-1 scores 57.1 (C) on agent readiness against Drex Max v1's 55.5 (C), and leads in 2 of 4 scored categories. Drex Max v1 leads on reach and agent interface. Both do decision models.", "tutorials": [], "verdicts": { "drex-max-v1": "A 27B cousin for typed decisions over text and screenshots, several questions per request with a probability for each option. Images need an NVIDIA GPU and Nace's loader; on Apple silicon only the text backbone runs, from 24 GB. The licence isn't open source, with free commercial use only under $1 million in revenue and funding.", "joey-1": "A very small cousin for routing, triage and guardrail checks, answering several typed questions about one state, with text or images, as probabilities from one prefill. It fits an 8 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are weak results on the Decision Index's new-domain tests and no safety results." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1", "json": "https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1.min.md" }, "markdown": "joey-1 scores 57.1 (C) on agent readiness against Drex Max v1's 55.5 (C), and leads in 2 of 4 scored categories. Drex Max v1 leads on reach and agent interface. Both do decision models.\n\n- Drex Max v1: grade C, 55.5/100, rank #90 of 120 open-weight models. Markdown https://www.anchorterminal.com/tools/drex-max-v1.md · JSON https://www.anchorterminal.com/api/v1/tools/drex-max-v1.json\n- joey-1: grade C, 57.1/100, rank #80 of 120 open-weight models. Markdown https://www.anchorterminal.com/tools/joey-1.md · JSON https://www.anchorterminal.com/api/v1/tools/joey-1.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 200 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Drex Max v1 (C)\n\nGood for: Agents that want self-hosted routing, triage or screen decisions with probabilities, on a CUDA GPU with 48 GB or more for images or a 24 GB Mac for text, where the Open RAIL-M terms fit.\n\nAhead on:\n- Reach, 65 against 60\n- Agent interface, 80 against 70\n\nWatch for: The licence bars commercial use above $1 million in revenue or funding and by anyone with a competing product, and restricts the outputs too\n\n### joey-1 (C)\n\nGood for: Agents that want self-hosted, low-cost ticket routing or guardrail checks with probabilities to threshold, on a GPU with 8 GB, and can accept a patched runtime.\n\nAhead on:\n- Risk, 55 against 45\n- Documentation and upkeep, 54 against 41\n\nWatch for: Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support\n\n\n## Score by category\n\n| Category | Weight | Drex Max v1 | joey-1 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 65 | 60 | Drex Max v1 +5 |\n| Risk | 20% (20 this run) | 45 | 55 | joey-1 +10 |\n| Agent interface | 10% (10 this run) | 80 | 70 | Drex Max v1 +10 |\n| Documentation and upkeep | 10% (10 this run) | 41 | 54 | joey-1 +13 |\n| Negative events | ≤15 | -2 | -2 | |\n| **Total** | | **55.5 · C** | **57.1 · C** | |\n\n## Facts side by side\n\n| Fact | Drex Max v1 | joey-1 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Nace AI, Inc. (Nace.AI) | Baseten |\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 | Nace.AI Open RAIL-M License (modified), version 1.0, October 2026, in the repository's LICENSE. Not an open-source licence. Use is free only for individuals and organisations under $1 million in revenue in the prior 12 months and under $1 million in total funding (personal and research use excepted), never by anyone with a product that competes with Nace's, decision models included, and under use restrictions that bind the model, its derivatives and its outputs. Built on Qwen/Qwen3.8-27B (Apache-2.0), whose licence text isn't carried in the repository | MIT, named in the card's metadata (license: mit) since the upload of 27 October 2026, with no LICENSE file. The base Qwen/Qwen3.5-2B is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-30 | 2026-10-29 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n\n## Verdicts\n\n**Drex Max v1.** A 27B cousin for typed decisions over text and screenshots, several questions per request with a probability for each option. Images need an NVIDIA GPU and Nace's loader; on Apple silicon only the text backbone runs, from 24 GB. The licence isn't open source, with free commercial use only under $1 million in revenue and funding.\n\n**joey-1.** A very small cousin for routing, triage and guardrail checks, answering several typed questions about one state, with text or images, as probabilities from one prefill. It fits an 8 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are weak results on the Decision Index's new-domain tests and no safety results.\n\n## Before you call either\n\n### Drex Max v1\n\n1. Clone github.com/nace-ai/drex-decision-models, download nace-ai/drex-max-v1 and run `python -m drex_max --model weights/drex-max-v1 --request examples/request.json` on an NVIDIA GPU\n2. Plan for about 49 GB of GPU memory in BF16, or about 26 GB with --8bit on CUDA, before any long context\n3. Don't load it with stock Transformers, vLLM or llama.cpp. Its full-attention layers must run non-causally with readout.safetensors applied, which only Nace's loader and forks do\n4. On a Mac with 24 GB or more, run `kapitsa-systemone --model ./drex-max-v1-affine-q4 --port 8000 --context 2048` for text-only decisions at POST /v1/systemone\n5. Raise the 16,384-token default with DREX_MAX_CONTEXT=N or --max-length N, up to 262,144, and expect more memory\n6. Check the licence first. Above $1 million in revenue or funding, or with a competing product, you need Nace's commercial licence\n\n### joey-1\n\n1. Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with `hf download baselabs/joey-1 --local-dir joey-1 \u0026\u0026 bash joey-1/setup.sh`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit\n2. Then call `DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\").decide(SystemOneRequest(state=..., questions=...))` from qev, as the card shows\n3. Don't load it with stock vLLM or Transformers. They ignore the block-bidirectional attention in config.json's modeling_overrides and give probabilities the model wasn't trained for\n4. Keep each request under 16,384 tokens, the trained length, or the engine refuses it\n5. Expect weaker answers on domains unlike its training mix, and threshold on the returned probability before acting\n6. Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-joey-2b-latest with a Baseten key\n\n## Questions\n\n### Which is better for AI agents, Drex Max v1 or joey-1?\n\njoey-1 scores 57.1 (C) on agent readiness against Drex Max v1's 55.5 (C), and leads in 2 of 4 scored categories. Drex Max v1 leads on reach and agent interface.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"drex-max-v1\", \"b\": \"joey-1\"}`. From a terminal: `anchor compare drex-max-v1 joey-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/drex-max-v1.json and https://www.anchorterminal.com/api/v1/tools/joey-1.json\n\n## Other comparisons with Drex Max v1 or joey-1\n\n- [Drex Max v1 vs elephant-1](https://www.anchorterminal.com/compare/drex-max-v1-vs-elephant-1.md)\n- [Drex Max v1 vs JEV-27B-VL](https://www.anchorterminal.com/compare/drex-max-v1-vs-jev-27b-vl.md)\n- [Drex Max v1 vs mammoth-1](https://www.anchorterminal.com/compare/drex-max-v1-vs-mammoth-1.md)\n- [elephant-1 vs joey-1](https://www.anchorterminal.com/compare/elephant-1-vs-joey-1.md)\n- [JEV-27B-VL vs joey-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.md)\n- [joey-1 vs mammoth-1](https://www.anchorterminal.com/compare/joey-1-vs-mammoth-1.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": "2026-10-31", "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": "Drex Max v1 vs joey-1", "url": "" } ], "description": "joey-1 scores 57.1 (C) to Drex Max v1's 55.5 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Drex Max v1 C 55.5", "joey-1 C 57.1", "scores" ], "h1": "Drex Max v1 vs joey-1", "image": "https://www.anchorterminal.com/assets/og/compare-drex-max-v1-vs-joey-1.png", "path": "/compare/drex-max-v1-vs-joey-1", "published": "2026-10-01", "section": "tools", "title": "Drex Max v1 vs joey-1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/drex-max-v1-vs-joey-1" }, "tokens": { "markdown": 2050, "slim": 630 }, "version": 1 }