https://www.anchorterminal.com/tools/qwen3-asr-0-6b Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-ASR-0.6B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/qwen3-asr-0-6b#rev_4011 https://www.anchorterminal.com/tools/qwen3-asr-0-6b#rev_4011 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba added the Transformers-layout -hf repositories beside the originals and dated the change in the README news on 26 June 2026, replacing nothing. That -hf template was updated for custom hotwords on 22 July, 91 days ago. The original repository and the qwen_asr code last changed on 30 January. None of the 9 discussions here, nor the three on the -hf repository, has a Qwen reply, and a vllm serve error report waits. 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-asr-0-6b#rev_4012 https://www.anchorterminal.com/tools/qwen3-asr-0-6b#rev_4012 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba's Transformers-native repository is 1.58 GB in BF16 and the original 1.88 GB, and ggml-org's Q8_0 GGUF is 1.02 GB. The card recommends a GPU with FlashAttention 2 but gives no memory figure. Apache 2.0 is named in the metadata, with the text in the GitHub repository rather than on the Hub. DeepInfra is the one live host. Model Studio's paid Qwen3-ASR-Flash isn't identified as these weights, so it isn't a priced fallback. 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-asr-0-6b#rev_4013 https://www.anchorterminal.com/tools/qwen3-asr-0-6b#rev_4013 Wed, 21 Oct 2026 00:00:00 +0000 review Alibaba documents audio as a path, URL, base64 or array, a forced language and free-text context, with the output parsed into language and transcript by parse_asr_output or Transformers' decode. vLLM's transcription endpoint and streaming are documented, but streaming drops batching and timestamps, and timestamps need Qwen3-ForcedAligner-0.6B. The Open ASR Leaderboard records 6.24 English short-form WER and 10.37 multilingual for the -hf build, against 6.56 multilingual for the 1.7B. 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-asr-0-6b#rev_4014 https://www.anchorterminal.com/tools/qwen3-asr-0-6b#rev_4014 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-ASR-0.6B's safetensors load through vLLM, SGLang or Transformers code, with prompts from the shipped chat template, and the weights carry a SHA-256 in the Qwen organisation. The card's Docker example mounts the host's Docker socket into the container with no caution, which gives the container control of the host's Docker daemon. Transcripts reach an agent as untrusted text, and nothing on the card addresses that. No safety results or reporting route 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-asr-0-6b https://www.anchorterminal.com/tools/qwen3-asr-0-6b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-ASR-0.6B is Alibaba's compact open-weight speech recognition model for 30 languages and 22 Chinese dialects, with language identification, context hints and streaming, published on Hugging Face in BF16 under Apache 2.0.