https://www.anchorterminal.com/tools/qwen3-5-2b Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3.5-2B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-5-2b#rev_3999 https://www.anchorterminal.com/tools/qwen3-5-2b#rev_3999 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen published the 2B on 2 March 2026 and the last commit, a README update, is from that day, 233 days before this check. None of the 6 discussions that aren't pull requests has a comment from a Qwen member. Pull request 6, a template fix for empty historical think blocks from 8 April, and pull request 14, adding the missing generation_config.json from 24 August, wait unreviewed. Qwen3-1.7B stays in its own repository without a note. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4000 https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4000 Wed, 21 Oct 2026 00:00:00 +0000 review Any 8 GB machine runs it. The Q4_K_M builds from Ollama and LM Studio, vision projector included, are 1.9 GB, and Ollama's default Q8_0 is 2.7 GB. BF16 is 4.6 GB. Apache 2.0, no use policy, no gate. Alibaba publishes no quantised 2B. Featherless AI is the one inference provider found, and whether Alibaba Model Studio hosts it is unchecked. At this size the hardware cost is small enough that hosting matters less. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4001 https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4001 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3.5-2B ships the family template, which renders several tool_call blocks per turn, and its card names qwen3_coder, though the format itself lives only in the template. Thinking is off by default and the card shows how to turn it on, not where the reasoning returns. A template fix for empty historical think blocks has waited since 8 April. Independent results are mixed, about 82 per cent on Artificial Analysis's tau2-bench Telecom run and 0.21 on AA-LCR. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4002 https://www.anchorterminal.com/tools/qwen3-5-2b#rev_4002 Wed, 21 Oct 2026 00:00:00 +0000 review Nothing from the Qwen3.5-2B repository runs on load. It's one safetensors file read by the released qwen3_5 code, and every file is hashed on the Hub in the Qwen organisation that QwenLM links to. Apache 2.0 carries no use policy or threshold. The rest of this lens is undocumented. The card publishes no safety results and no guidance beyond a note on thinking loops, and neither QwenLM/Qwen3.5 nor QwenLM/.github has a SECURITY.md. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-5-2b https://www.anchorterminal.com/tools/qwen3-5-2b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3.5-2B is a small model in Alibaba's Qwen3.5 family, 2B language parameters with a vision encoder, thinking off by default and a 262,144-token context, published on Hugging Face in BF16 under Apache 2.0 for prototyping, fine-tuning and research.