https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-Coder-30B-A3B-Instruct. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#rev_4019 https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#rev_4019 Wed, 21 Oct 2026 00:00:00 +0000 review On 3 December 2025, 322 days ago, Alibaba corrected config.json's architecture fields in place, after template and parser updates on 7 and 21 August 2025 merged from pull requests. Commit titles name what was touched but not what changed, and the card has no note. One of 26 discussions has a reply from a Hub-flagged Qwen member who appears to be an outside quantiser. Reports titled about the vLLM parser and an attention_bias error wait. 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-coder-30b-a3b-instruct#rev_4020 https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#rev_4020 Wed, 21 Oct 2026 00:00:00 +0000 review Ollama's qwen3-coder:30b is 19 GB at Q4_K_M and LM Studio's MLX 4-bit 17.19 GB, both in the 24 GB band and neither under 16 GB. Alibaba's own quantisation is FP8 at 31.2 GB. Apache 2.0 with no use policy, ungated. Featherless AI, SiliconFlow and Amazon Bedrock serve it at 262,144 tokens of context, so a hosted route exists, though the dossier gives none of their per-token prices. 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-coder-30b-a3b-instruct#rev_4021 https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#rev_4021 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen ships its own tool parser in the repository, registered for vLLM as qwen3_coder, and the card's Agentic Coding section declares tools in the OpenAI format. The card's example stops before a call comes back, so the returned shape is read from the template and parser. Several calls fit one turn. There's no thinking and no documented JSON output, and parser reports in the discussions wait. Artificial Analysis records about 35 per cent on tau2-bench Telecom among 9 independent results. 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-coder-30b-a3b-instruct#rev_4022 https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#rev_4022 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-Coder-30B-A3B-Instruct ships safetensors and a qwen3coder_tool_parser.py that neither loading nor prompting runs, since vLLM and SGLang carry their own parsers. All 16 shards and tokenizer.json have a SHA-256. The card and README present it for agents that run commands, browse and edit files, and say nothing on prompt injection or safeguards. No safety results exist beyond a pretraining filter label. The README lists WeChat and Discord, which aren't a reporting route. 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-coder-30b-a3b-instruct https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-Coder-30B-A3B-Instruct is Alibaba's open-weight mixture-of-experts coding model, 30.5B parameters with 3.3B active, for agentic coding and tool use, with a 262,144-token context, published in BF16 and FP8 under Apache 2.0.