https://www.anchorterminal.com/tools/qwen3-6-35b-a3b Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3.6-35B-A3B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3811 https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3811 Wed, 21 Oct 2026 00:00:00 +0000 review Last edited on 24 April 2026, a README change 180 days before this check, Qwen3.6-35B-A3B has had nothing since its 16 April release and the licence added on 22 April. None of the 61 discussions that aren't pull requests had a reply from any of the Qwen organisation's 194 members. Reports titled as tool calling, think-tag and architecture-tag faults remain open. Qwen3.5-35B-A3B stays in its own repository with no note pointing to its successor. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3812 https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3812 Wed, 21 Oct 2026 00:00:00 +0000 review Apache 2.0, commercial use free, nothing gated. Alibaba's smallest build is FP8 at 37.5 GB, and BF16 is 71.9 GB. Ollama's default 35b build is 23 to 24 GB, which with headroom for context needs a 32 GB machine rather than a 24 GB card. The card's examples use 8 GPUs and state no memory needs. DeepInfra, Featherless AI and Scaleway host it and the card names Alibaba Cloud Model Studio, with no prices in the dossier. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3813 https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3813 Wed, 21 Oct 2026 00:00:00 +0000 review Thinking, preserved thinking and sampling for three modes are covered on the card, with requests for text, image and video and a Qwen-Agent example with an MCP server. Tools are declared through Qwen-Agent, but how calls come back is defined only by the template, with qwen3_coder named in the serving commands. Structured output isn't documented. Of 14 independent results, tau2-bench Telecom sits near the leading result while Artificial Analysis records 0.0 on Terminal-Bench 4.0. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3814 https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#rev_3814 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3.6-35B-A3B loads from 26 safetensors shards through the model code in Transformers, vLLM and SGLang and a Jinja template, with no trust_remote_code and a SHA-256 per weight file. Beyond the files the card is silent on risk, with no safety results, refusal statement, cautions or injection guidance. There's no security.txt, as qwen.ai redirects to its home page, and no SECURITY.md in QwenLM/Qwen3.6. Whether Alibaba's group security centre takes Qwen reports is unchecked. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-6-35b-a3b https://www.anchorterminal.com/tools/qwen3-6-35b-a3b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3.6-35B-A3B is Alibaba's open-weight mixture-of-experts vision-language model, 35B parameters with 3B active and a 262,144-token context, published on Hugging Face in BF16 and FP8 under Apache 2.0.