https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-VL-30B-A3B-Instruct. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#rev_4051 https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#rev_4051 Wed, 21 Oct 2026 00:00:00 +0000 review The weight files date from 30 September 2025 and the repository last changed on 26 November with a library tag. The latest code change was the qwen-vl-utils patch-size fix of 4 January 2026, 290 days ago. Config, tokenizer config, template and card agree on 262,144 tokens and the qwen3_vl_moe architecture, and no broken-file report waits. None of the 8 discussions that aren't pull requests has a Qwen reply. 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-30b-a3b-instruct#rev_4052 https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#rev_4052 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba's Q4_K_M GGUF is 18.56 GB and its Q8_0 vision file 0.71 GB, about 23 GB with the margin, so one 24 GB card. Ollama's build is 20 GB, right at 24 GB with the margin. FP8 from Alibaba is 32.3 GB. Apache 2.0, ungated. Novita, Featherless AI, DeepInfra and SiliconFlow serve it in FP8 or BF16, so per-token use is open, though the dossier quotes no rate. 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-30b-a3b-instruct#rev_4053 https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#rev_4053 Wed, 21 Oct 2026 00:00:00 +0000 review Artificial Analysis records about 62 per cent on MMMU-Pro for Qwen3-VL-30B-A3B-Instruct, but about 19 per cent on tau2-bench Telecom, among 9 independent results. The tool format sits only in the template, Hermes-style JSON in tool_call tags, and Alibaba names no parser; the qwen parser comes from SGLang's cookbook. The report describes multimodal function-calling training, and several calls fit one turn. No thinking and no JSON output are documented for this edition. 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-30b-a3b-instruct#rev_4054 https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#rev_4054 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-VL-30B-A3B-Instruct loads through Qwen3VLMoeForConditionalGeneration with its prompt from chat_template.json, and none of its three repositories holds Python. SHA-256 hashes cover every weight and GGUF file. Like the other Qwen3-VL sizes, its card pitches GUI agent use and gives no prompt-injection guidance, refusal scope or cautions, and the technical report publishes no safety results. Apache 2.0 is unchanged since release. No reporting route for Qwen 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-30b-a3b-instruct https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-VL-30B-A3B-Instruct is Alibaba's open-weight vision-language mixture of experts with about 31B parameters and 3B active, taking text, images and video with a 262,144-token context, published on Hugging Face in BF16, FP8 and GGUF under Apache 2.0.