https://www.anchorterminal.com/tools/qwen3-5-397b-a17b Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3.5-397B-A17B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4003 https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4003 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen merged a KTransformers guide on 20 February and a corrected medical VQA result on 15 March 2026, and the last commit is a README fix on 24 April, 180 days ago. Since then, none of the 40 most recent discussions has a reply from Alibaba's staff. The one member reply came from Unsloth. A template bug report from 4 March, a template and tool-parser mismatch report from 3 April and a template fix from 8 April wait. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4004 https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4004 Wed, 21 Oct 2026 00:00:00 +0000 review Self-hosting starts at Alibaba's GPTQ-Int4 build of 235.8 GB, about 283 GB with the margin, or LM Studio's MLX 4-bit at 223.9 GB, which its catalogue says needs 230 GB of system memory. Nothing fits a 256 GB machine. The card names Qwen3.5-Plus on Alibaba Cloud Model Studio as the hosted version, and five providers are live on Hugging Face, but no per-token rate is in the dossier. Apache 2.0, ungated. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4005 https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4005 Wed, 21 Oct 2026 00:00:00 +0000 review Seventeen independent results back this model, including 97.81 on the tau-bench leaderboard's tau2-bench Telecom and 9.79 on tau3-Banking. Thinking turns off per request and comes back in think tags split by the qwen3 parser. The card names qwen3_coder but leaves the declaration and call format to the template, and documents no JSON output. Artificial Analysis records 0.0 on Terminal-Bench 4.0, against about 51 per cent on 2.1. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4006 https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#rev_4006 Wed, 21 Oct 2026 00:00:00 +0000 review The flagship Qwen3.5 runs from 94 safetensors shards with no repository code, and all 95 LFS files carry a SHA-256 in the Qwen organisation. The card's SecCodeBench row measures secure code generation, a capability, and no evaluation of the model's own behaviour is published. Nothing addresses prompt injection or safeguards. qwen.ai redirects security.txt to its home page, QwenLM/Qwen3.5 has no SECURITY.md, and Alibaba's response centre couldn't be checked. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-397b-a17b https://www.anchorterminal.com/tools/qwen3-5-397b-a17b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3.5-397B-A17B is Alibaba's largest open-weight Qwen3.5 model, a mixture-of-experts vision-language model of 397B parameters with 17B active, thinking on by default and a 262,144-token context, published on Hugging Face in BF16, FP8 and GPTQ 4-bit under Apache 2.0.