https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-VL-2B-Instruct. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#rev_4047 https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#rev_4047 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-VL-2B's weights last changed on 23 October 2025 and the GGUF build on 1 November. The latest change to code that runs it was a qwen-vl-utils fix on 4 January 2026. The GGUF card's llama-server example names the 235B model's vision file, which this repository doesn't hold. None of the 13 discussions that aren't pull requests has a Qwen reply, including a report that batched and single outputs differ. 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-vl-2b-instruct#rev_4048 https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#rev_4048 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba's own Q4_K_M GGUF is 1.11 GB plus a 0.45 GB vision file, about 1.9 GB with the margin, and its FP8 build is 3.48 GB. Any laptop holds either. Apache 2.0 with no use policy, ungated across BF16, FP8 and GGUF. Featherless is the only host found. DeepInfra, Novita and Parasail don't list it, and whether Model Studio does couldn't be read, so a hosted route rests on one provider. 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-vl-2b-instruct#rev_4049 https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#rev_4049 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-VL-2B-Instruct's tool calls are defined only by its template, JSON in tool_call tags with results in tool_response, and the card never mentions tool calling. The qwen parser name comes from SGLang's cookbook, not Alibaba. The family report describes multimodal function-calling training and the template allows several calls a turn. There's no thinking, no JSON output guidance, and nobody independent has benchmarked it, so the agent evidence rests on Alibaba's report. 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-vl-2b-instruct#rev_4050 https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#rev_4050 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-VL-2B-Instruct is sold on its card as a visual agent that operates PC and phone interfaces, and that's where the blast radius sits. The files are clean, safetensors and GGUF with no Python and a SHA-256 on every weight file, and the FP8 card's trust_remote_code flag has nothing to load. The card gives no prompt-injection guidance, no statement of refusals and no cautions. The technical report has no safety results, and no security contact was found. 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-vl-2b-instruct https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-VL-2B-Instruct is Alibaba's open-weight dense vision-language model of about 2B parameters, taking text, images and video with a 262,144-token context, published on Hugging Face in BF16, FP8 and GGUF under Apache 2.0.