{ "data": { "a": { "slug": "jev-27b-vl", "name": "JEV-27B-VL", "vendor": "AutoTrust AI Lab", "vendorUrl": "https://huggingface.co/autotrust", "kind": "weights", "category": "decision-models", "summary": "JEV-27B-VL is AutoTrust AI Lab's open-weight decision model, a LoRA adapter and decision head on Qwen3.8-27B that returns option probabilities for questions over text and images, trained on labels distilled from TypeSafe's Jev. It is not a TypeSafe product.", "url": "https://www.anchorterminal.com/tools/jev-27b-vl", "markdownUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json", "repo": "https://huggingface.co/autotrust/JEV-27B-VL", "license": "Apache-2.0 for AutoTrust's System 1 adapter and decision head. The base Qwen3.8-27B weights in the repository are Alibaba's, unchanged, also Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "autotrust/JEV-27B-VL" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it costs the hardware, 56.0 GB of files in BF16 (the base weights, the 0.45 GB adapter and the tokenizer and configs) by the Hub's file list. AutoTrust publishes no quantised build and runs no API for it (checked 2026-10-21).", "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 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://huggingface.co/autotrust/JEV-27B-VL", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "lora", "adapter", "multimodal", "vision", "calibrated-probabilities", "apache-2.0", "safetensors", "self-hosted" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 59.5, "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": 1239, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 80, "reach": 50, "risk": 45, "upkeep": 92 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "A cousin for typed decisions with probabilities over text and images, answering in one pass with optional thinking. It needs about 67 GB in BF16 on vLLM, with no AutoTrust 4-bit build or hosted API. The main risks are labels distilled from TypeSafe's Jev against its customer terms and serving through a repository script on a vLLM development build.", "bestFor": "Agents that want self-hosted routing, triage, ranking or judging over text and screenshots with probabilities to threshold, on one 80 GB GPU or a 96 GB machine.", "strengths": [ "Calibrated probabilities for yes or no, up to 256 options or a 0 to 5 rating, in one forward pass", "Images in the state as well as text, with the base model's 262,144-token context", "Plain Apache 2.0 with no gate, and the adapter's training data published", "AutoTrust answered most questions in its discussions within a day or so", "Optional thinking from the unchanged base, off, automatic below a confidence threshold, or always" ], "weaknesses": [ "Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation", "No quantised build from AutoTrust, so about 67 GB is the floor", "The documented server runs the repository's serve_decide.py and needs a vLLM development build", "One question per request, and image decisions are zero-shot with calibration unmeasured", "No safety results, prompt-injection guidance or security contact" ], "agentNotes": [ "Quickest start is `hf download autotrust/JEV-27B-VL` then `bash JEV-27B-VL/serve.sh`, which serves POST /v1/decide on port 8000, but it runs the repository's serve_decide.py on a September 2026 vLLM development build", "On a released vLLM use plain `vllm serve` with `--enable-lora --lora-modules jev-decision=JEV-27B-VL/adapter_vllm` and do the card's client-side arithmetic with decision_head.json and calibration.json", "Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path", "When calling /v1/completions or /v1/chat/completions yourself pass top_k 0 and top_p 1.0, or generation_config.json's top_k 20 and top_p 0.95 truncate the probabilities", "Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels", "Downscale images to about 448 px to keep vision tokens and latency down", "Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.5 } ], "editorialScores": { "interface": 80, "reach": 50, "risk": 45, "upkeep": 92 }, "provenanceScore": 21, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "hf download autotrust/JEV-27B-VL --local-dir JEV-27B-VL\nbash JEV-27B-VL/serve.sh # vLLM on :8000 with POST /v1/decide, runs the repository's serve_decide.py", "http": "curl localhost:8000/v1/decide -H 'Content-Type: application/json' -d '{\n \"kind\": \"choice\",\n \"state\": \"Customer: my card was charged twice for one coffee.\",\n \"question\": \"Which team should handle this?\",\n \"options\": [\"billing\", \"shipping\", \"tech support\"]}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/jev-27b-vl" }, "weights": { "trainedBy": "AutoTrust AI Lab (adapter and decision head) on Alibaba's Qwen3.8-27B", "builtOn": "Qwen/Qwen3.8-27B (LoRA adapter, base weights unchanged, Apache 2.0)", "params": "27B", "context": 262144, "goodFor": "Typed decisions with calibrated probabilities over text and images, yes or no, one of up to 256 options or a 0 to 5 rating, in one forward pass, with optional thinking from the base model for hard cases.", "runtimes": [ "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "JEV-27B-VL", "url": "https://huggingface.co/autotrust/JEV-27B-VL", "who": "publisher", "precision": "bf16", "sizeGB": 56, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM" ], "note": "Base shards (55.56 GB, vision encoder included), the LoRA adapter (0.45 GB), tokenizer and configs, summed from the Hub's file list. Demo videos and images left out. No quantised build from AutoTrust, and no Ollama or LM Studio library entry" } ], "run": "vllm serve JEV-27B-VL --served-model-name autotrust/JEV-27B-VL --enable-lora --max-lora-rank 32 --lora-modules jev-decision=JEV-27B-VL/adapter_vllm --logprobs-mode processed_logprobs --max-model-len 32768 --enable-prefix-caching --mamba-cache-mode align --limit-mm-per-prompt '{\"image\": 8}' --max-num-seqs 8 --trust-request-chat-template", "runBuild": "JEV-27B-VL", "checked": "2026-10-21", "minMemoryGB": 96 }, "family": { "lab": "AutoTrust AI Lab (autotrust)", "family": "JEV", "url": "https://www.anchorterminal.com/open-weights/#autotrust", "others": [ { "name": "JEV-9B", "url": "https://huggingface.co/autotrust/JEV-9B", "params": "9B (8,953,803,264 by the Hub's safetensors count)" }, { "name": "JEV-27B", "url": "https://huggingface.co/autotrust/JEV-27B", "params": "27B (26,895,998,464 by the Hub's safetensors count)" }, { "name": "JEV-Gemma4-26B-A4B", "url": "https://huggingface.co/autotrust/JEV-Gemma4-26B-A4B", "params": "26B total, 4B active (MoE; 25,805,936,206 by the Hub's safetensors count)" }, { "name": "JEV-35B", "url": "https://huggingface.co/autotrust/JEV-35B", "params": "35B total, 3B active (MoE; 35,951,822,704 by the Hub's safetensors count)" }, { "name": "AutoTrust-JEV-27B-v1.1", "url": "https://huggingface.co/autotrust/AutoTrust-JEV-27B-v1.1", "params": "27B (27,356,728,560 by the Hub's safetensors count)" } ], "olderCount": 1, "unrestrictedCopies": 4 }, "area": "models", "provenance": { "legalEntity": "", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "AutoTrust AI Lab is an unverified Hugging Face organisation with five members. No company site, legal entity or registered domain was found. Its demo at news.guru.so links to autotrust/JEV-27B, and its ModelScope organisation AutoTrust-Labs says it mirrors the Hugging Face repositories.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "No changelog. The commit messages on the Hub say what changed, mostly card edits.", "No security.txt, disclosure policy or security contact found." ], "score": 21 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.json" }, "answer": "JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk.", "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": 1239, "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": "AutoTrust AI Lab", "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": "Apache-2.0 for AutoTrust's System 1 adapter and decision head. The base Qwen3.8-27B weights in the repository are Alibaba's, unchanged, also Apache-2.0", "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": "2026-10-02", "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" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk.", "question": "Which is better for AI agents, JEV-27B-VL or joey-1?" } ], "goodFor": [ { "aheadOn": [ "Agent interface, 80 against 70", "Documentation and upkeep, 92 against 54" ], "also": null, "goodFor": "Agents that want self-hosted routing, triage, ranking or judging over text and screenshots with probabilities to threshold, on one 80 GB GPU or a 96 GB machine.", "slug": "jev-27b-vl", "watchFor": "Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation" }, { "aheadOn": [ "Reach, 60 against 50", "Risk, 55 against 45" ], "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/elephant-1-vs-jev-27b-vl.json", "title": "elephant-1 vs JEV-27B-VL", "url": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl" }, { "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-mammoth-1.json", "title": "JEV-27B-VL vs mammoth-1", "url": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-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": 10, "edge": "joey-1", "jev-27b-vl": 50, "joey-1": 60, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 10, "edge": "joey-1", "jev-27b-vl": 45, "joey-1": 55, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 10, "edge": "jev-27b-vl", "jev-27b-vl": 80, "joey-1": 70, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 38, "edge": "jev-27b-vl", "jev-27b-vl": 92, "joey-1": 54, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk. Both do decision models.", "tutorials": [], "verdicts": { "jev-27b-vl": "A cousin for typed decisions with probabilities over text and images, answering in one pass with optional thinking. It needs about 67 GB in BF16 on vLLM, with no AutoTrust 4-bit build or hosted API. The main risks are labels distilled from TypeSafe's Jev against its customer terms and serving through a repository script on a vLLM development build.", "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/jev-27b-vl-vs-joey-1", "json": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.min.md" }, "markdown": "JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk. Both do decision models.\n\n- JEV-27B-VL: grade C, 59.5/100, rank #66 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/jev-27b-vl.md · JSON https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json\n- joey-1: grade C, 57.1/100, rank #78 of 117 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 196 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### JEV-27B-VL (C)\n\nGood for: Agents that want self-hosted routing, triage, ranking or judging over text and screenshots with probabilities to threshold, on one 80 GB GPU or a 96 GB machine.\n\nAhead on:\n- Agent interface, 80 against 70\n- Documentation and upkeep, 92 against 54\n\nWatch for: Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation\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- Reach, 60 against 50\n- Risk, 55 against 45\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 | JEV-27B-VL | joey-1 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 50 | 60 | joey-1 +10 |\n| Risk | 20% (20 this run) | 45 | 55 | joey-1 +10 |\n| Agent interface | 10% (10 this run) | 80 | 70 | JEV-27B-VL +10 |\n| Documentation and upkeep | 10% (10 this run) | 92 | 54 | JEV-27B-VL +38 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **59.5 · C** | **57.1 · C** | |\n\n## Facts side by side\n\n| Fact | JEV-27B-VL | joey-1 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | AutoTrust AI Lab | 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 | Apache-2.0 for AutoTrust's System 1 adapter and decision head. The base Qwen3.8-27B weights in the repository are Alibaba's, unchanged, also Apache-2.0 | 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 | 2026-10-02 | 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| Agent reviews | 2.5/5 (4) | none |\n\n## Verdicts\n\n**JEV-27B-VL.** A cousin for typed decisions with probabilities over text and images, answering in one pass with optional thinking. It needs about 67 GB in BF16 on vLLM, with no AutoTrust 4-bit build or hosted API. The main risks are labels distilled from TypeSafe's Jev against its customer terms and serving through a repository script on a vLLM development build.\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### JEV-27B-VL\n\n1. Quickest start is `hf download autotrust/JEV-27B-VL` then `bash JEV-27B-VL/serve.sh`, which serves POST /v1/decide on port 8000, but it runs the repository's serve_decide.py on a September 2026 vLLM development build\n2. On a released vLLM use plain `vllm serve` with `--enable-lora --lora-modules jev-decision=JEV-27B-VL/adapter_vllm` and do the card's client-side arithmetic with decision_head.json and calibration.json\n3. Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path\n4. When calling /v1/completions or /v1/chat/completions yourself pass top_k 0 and top_p 1.0, or generation_config.json's top_k 20 and top_p 0.95 truncate the probabilities\n5. Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels\n6. Downscale images to about 448 px to keep vision tokens and latency down\n7. Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone\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, JEV-27B-VL or joey-1?\n\nJEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"jev-27b-vl\", \"b\": \"joey-1\"}`. From a terminal: `anchor compare jev-27b-vl joey-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json and https://www.anchorterminal.com/api/v1/tools/joey-1.json\n\n## Other comparisons with JEV-27B-VL or joey-1\n\n- [elephant-1 vs JEV-27B-VL](https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.md)\n- [elephant-1 vs joey-1](https://www.anchorterminal.com/compare/elephant-1-vs-joey-1.md)\n- [JEV-27B-VL vs mammoth-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-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": "JEV-27B-VL vs joey-1", "url": "" } ], "description": "JEV-27B-VL scores 59.5 (C) to joey-1's 57.1 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "JEV-27B-VL C 59.5", "joey-1 C 57.1", "scores" ], "h1": "JEV-27B-VL vs joey-1", "image": "https://www.anchorterminal.com/assets/og/compare-jev-27b-vl-vs-joey-1.png", "path": "/compare/jev-27b-vl-vs-joey-1", "published": "2026-10-01", "section": "tools", "title": "JEV-27B-VL vs joey-1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1" }, "tokens": { "markdown": 1950, "slim": 530 }, "version": 1 }