https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507 Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-30B-A3B-Instruct-2507. en Wed, 21 Oct 2026 22:14:21 +0000 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3983 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3983 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba last changed these files on 17 September 2025, a tokenizer_config.json update, 399 days before this check. The 1M-token files arrived on 8 August 2025 and the QwenLM/Qwen3 News list dates them. One of 23 discussions has a reply from a Hub-flagged Qwen member, who may be an outside contributor, and reports titled about the 1M mode and Dual Chunk Flash Attention in vLLM wait. GitHub issues weren't counted. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3984 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3984 Wed, 21 Oct 2026 00:00:00 +0000 review Ollama's Q4_K_M build is 19 GB and LM Studio's MLX 4-bit 17.19 GB, so a 24 GB card or Mac holds it but 16 GB doesn't. Alibaba's own smallest build is FP8 at 31.2 GB. Apache 2.0 with nothing added, ungated. Featherless AI, DekaLLM, SiliconFlow and Nebius host it, though the dossier quotes none of their per-token prices. The 1M-token mode is another matter, about 240 GB of GPU memory per the card. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3985 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3985 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen's Function Calling guide covers this edition's Hermes-style template, showing tools in tools tags, calls returned as tool_calls and vLLM's hermes parser. The template allows several calls a turn. This edition has no thinking, and JSON output is undocumented beyond vLLM's generic guided decoding; a discussion about structured output closed with no Qwen reply. Of 12 independent results, BFCL v4 records 41.39 overall and Artificial Analysis about 10 per cent on tau2-bench Telecom. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3986 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#rev_3986 Wed, 21 Oct 2026 00:00:00 +0000 review The 2507 Instruct edition loads from safetensors through AutoModelForCausalLM and a Jinja template, and the 1M mode swaps a config file rather than running code. All 16 shards carry a SHA-256 in the Qwen organisation, and Apache 2.0 has no use policy. The card's Agentic Use section connects it to MCP servers and a code interpreter, yet it says nothing on prompt injection, refusals or safeguards. No safety results and no reporting route for Qwen were 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/qwen3-30b-a3b-instruct-2507 https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-30B-A3B-Instruct-2507 is Alibaba's open-weight mixture-of-experts text model, 30.5B parameters with 3.3B active, the non-thinking edition of the July 2025 Qwen3 update, with a 262,144-token context, published in BF16 and FP8 under Apache 2.0.