Qwen

Qwen3-ASR-0.6B

Name: Qwen3-ASR-0.6B
Author: Qwen

← All models

0.9B parameters · Base · Qwen3 family

apache-2.0 hash verified source matched revision pinned

Which version should I download?

Default pick: GGUF · Q8_0 — Q8_0 GGUF (ggml-org, converted from official Qwen/Qwen3-ASR-0.6B) — near-lossless 8-bit lead for the 0.6B automatic-speech-recognition model; audio mmproj (Q8_0) bundled. Repo ships no plain Q4_K_M; Q8_0 is the accessible lead.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick?

Format	Level	Size	Verdict	Est. speed	Quality note	Swarm	Download
GGUF	Q8_0	767.47 MB	Set your rig	—	Q8_0 GGUF (ggml-org, converted from official Qwen/Qwen3-ASR-0.6B) — near-lossless 8-bit lead for the 0.6B automatic-speech-recognition model; audio mmproj (Q8_0) bundled. Repo ships no plain Q4_K_M; Q8_0 is the accessible lead.	2S / 0L webseed OK	Magnet .torrent

GGUF · Q8_0

767.47 MB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Q8_0 GGUF (ggml-org, converted from official Qwen/Qwen3-ASR-0.6B) — near-lossless 8-bit lead for the 0.6B automatic-speech-recognition model; audio mmproj (Q8_0) bundled. Repo ships no plain Q4_K_M; Q8_0 is the accessible lead.

Magnet .torrent

Run it

Runtime completeness (Q8_0 torrent): llama.cpp ✅ Ollama – vision sidecar –

– Ollama — runs the GGUF directly; no Modelfile bundled
– vision sidecar — not a vision model

Quant

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server

llama-server -m Qwen3-ASR-0.6B-Q8_0.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile)

FROM ./Qwen3-ASR-0.6B-Q8_0.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999

Create

ollama create qwen-qwen3-asr-0-6b -f Modelfile

Run

ollama run qwen-qwen3-asr-0-6b

GGUF is not a first-class vLLM format.

vLLM GGUF support is experimental and single-file only; prefer safetensors/GPTQ/AWQ for production. If you must, pass the .gguf path to `vllm serve` with --load-format gguf on a recent vLLM.

Load Qwen3-ASR-0.6B-Q8_0.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

Not an MLX-format quant.

MLX runs MLX-format weights only (Apple Silicon). This quant is not an MLX build.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance: https://huggingface.co/Qwen/Qwen3-ASR-0.6B
Revision pin: 5eb144179a02acc5e5ba31e748d22b0cf3e303b0
Manifest: Present

License

Name: apache-2.0
Commercial use: yes
Access: Open

File hashes (SHA-256)

qwen3-asr-0.6b-q8-0/LICENSE cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30
qwen3-asr-0.6b-q8-0/Qwen3-ASR-0.6B-Q8_0.gguf bca259818b50ca7c4c05e9bdb35a5dc04fa039653a6d6f3f0f331f96f6aa1971
qwen3-asr-0.6b-q8-0/README.md 9ce5165ae78d9d2c70ca6ed63c156b68e1d31f2a0834bfcfa5244309e0ded0f3
qwen3-asr-0.6b-q8-0/mmproj-Qwen3-ASR-0.6B-Q8_0.gguf 41a342b5e4c514e968cb756de6cd1b7be39eff43c44c57a2ef5fc6522e36603d

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Reviews & presets

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

No community reports yet.

Recommended download