{"v":1,"id":"model:hf:handy-computer/Qwen3-ASR-0.6B-gguf","slug":"model-handy-computer-qwen3-asr-0-6b-gguf","kind":"model","category":"speech","title":"Qwen3-ASR-0.6B-gguf","summary":"GGUF conversions of Qwen/Qwen3-ASR-0.6B for use with transcribe.cpp.","source":{"provider":"hf","ref":"handy-computer/Qwen3-ASR-0.6B-gguf","url":"https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf","rev":"28c66fba077f1359a42b52c55b618a24cdb6e0e7","fetchedAt":"2026-10-02T20:59:38.628Z","etag":"W/\"154f-kbVQIxwFijieQFgv+aYLAoFDdMs\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","open":true},"metrics":{"downloads":141419,"downloadsWeek":327838,"likes":3,"takenAt":"2026-10-02T20:59:38.628Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","qwen3","qwen3-asr","multilingual","automatic-speech-recognition","zh","en","yue","ar","de","fr","es","pt","id","it","ko","ru","th","vi","ja","tr","hi","ms","nl","sv","da","fi","pl","cs","fil","fa","el","ro","hu","mk","conversational"],"pipeline":"automatic-speech-recognition","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2026-09-15T07:05:43.000Z","collectedAt":"2026-10-02T20:59:38.628Z","review":{"numbers":["141,419 downloads on Hugging Face","3 likes","license apache-2.0","0.5 GB for Qwen3-ASR-0.6B-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:59:38.628Z","http":200},"description":"# Qwen3-ASR-0.6B: transcribe.cpp GGUF\n\nGGUF conversions of [Qwen/Qwen3-ASR-0.6B](https://huggingface.co/Qwen/Qwen3-ASR-0.6B) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[5eb1441](https://huggingface.co/Qwen/Qwen3-ASR-0.6B/commit/5eb1441),\npinned 2026-04-19.\nValidated against the qwen_asr 0.0.6 reference at transcribe.cpp commit\n[3f61df7](https://github.com/handy-computer/transcribe.cpp/tree/3f61df7)\non 2026-04-20.\n\nOffline multilingual speech-to-text. An 18-layer bidirectional audio encoder\nfeeds a 28-layer Qwen3 causal LM with audio-token injection (fused\naudio+text sequence, no cross-attention). Auto-detects the audio's language\nacross 30 languages and emits the transcript in that language. Takes a\n16 kHz mono WAV; explicit language hints are not supported at this time.\n\n## Downloads\n\n| Quantization | Download | Size | WER (LibriSpeech test-clean) |\n| --- | --- | ---: | ---: |\n| BF16 | [Qwen3-ASR-0.6B-BF16.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-BF16.gguf) | 1.57 GB | 2.12% |\n| F16 | [Qwen3-ASR-0.6B-F16.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-F16.gguf) | 1.58 GB | 2.12% |\n| Q8_0 | [Qwen3-ASR-0.6B-Q8_0.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-Q8_0.gguf) | 850 MB | 2.11% |\n| Q6_K | [Qwen3-ASR-0.6B-Q6_K.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-Q6_K.gguf) | 690 MB | 2.11% |\n| Q5_K_M | [Qwen3-ASR-0.6B-Q5_K_M.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-Q5_K_M.gguf) | 645 MB | 2.21% |\n| Q4_K_M | [Qwen3-ASR-0.6B-Q4_K_M.gguf](https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf/resolve/main/Qwen3-ASR-0.6B-Q4_K_M.gguf) | 590 MB | 2.26% |\n\nWER on the full LibriSpeech test-clean split (2,62…\n\nSource: https://huggingface.co/handy-computer/Qwen3-ASR-0.6B-gguf","install":{"kind":"model","hfId":"handy-computer/Qwen3-ASR-0.6B-gguf","gated":false,"format":"gguf","files":[{"name":"Qwen3-ASR-0.6B-BF16.gguf","size":1571490016,"quant":"BF16","sha256":"dadb8196937aa6b998a94124a043fce694e0ab6c3c6eb0ae1669fa49d04aab84"},{"name":"Qwen3-ASR-0.6B-F16.gguf","size":1579793056,"quant":"F16","sha256":"5c90e4b1a72a4c59cd12afa5ebb0cc8628848148f2b337d025cc5121ae4d2eea"},{"name":"Qwen3-ASR-0.6B-Q4_K_M.gguf","size":589560480,"quant":"Q4_K_M","sha256":"5b58f32a58ffa2c8783e0b0963485623e286e6272d953dfc9e28bc3447dee0c0"},{"name":"Qwen3-ASR-0.6B-Q5_K_M.gguf","size":645356192,"quant":"Q5_K_M","sha256":"062a7bcb18675c2fe5ffd0e8b354eac6a1ceada9b2af9ef7168746ae16b54358"},{"name":"Qwen3-ASR-0.6B-Q6_K.gguf","size":690417824,"quant":"Q6_K","sha256":"3b051f108f03c0c91bbe1a3b2c1ee15e3ed51e4caec2a48751b01f2a21441cc3"},{"name":"Qwen3-ASR-0.6B-Q8_0.gguf","size":850423456,"quant":"Q8_0","sha256":"f081b2d5e23bd669d92cc331d722a8a0681943b8e6f34b48996fd5c319b5acd8"}],"totalBytes":5927041024,"suggestedFile":"Qwen3-ASR-0.6B-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":589560480,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:handy-computer/Qwen3-ASR-0.6B-gguf"}}