Qwen3 ASR 0.6B HF
Qwen · released Jun 26, 2026 · Qwen/Qwen3-ASR-0.6B-hf
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 30
- Size
- 0.8B
Context measured in tokens
Our take
Written Sep 4, 2026Qwen3 ASR is a tiny downloadable speech-to-text model with a permissive Apache licence and support for 30 languages. It is unusually fast and handles messy real-world audio better than most, though clean read-aloud recordings are a relative weak spot.
Pick this for fast local transcription where speed matters — it processes an hour of audio in about five seconds on benchmark hardware. Use it for meeting-room or podcast audio, accent-heavy recordings, or multilingual pipelines needing broad language coverage. Skip it if you need commercial hosting, pristine accuracy on clean read-aloud speech, or verified quality in non-English languages.
The case for it
- Extremely fast: 730× real-time on benchmark hardware with a 0.8-billion-parameter footprint.
- Strong on messy real-world audio: better than most models on podcasts, recorded meetings and accented speech.
- Truly permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Broad language coverage for its size: 30 languages including Chinese, Arabic, German, French, Spanish and Portuguese.
The case against it
- Clean read-aloud audio is a relative weak spot at 1.7% word error, worse than the 1.4% median.
- No commercial hosting options currently available; you must run it yourself.
- High absolute error rates on challenging audio despite decent relative standing — roughly one word in nine or ten still wrong on meetings and accented speech.
How good is it?
An open transcription model for turning podcasts and video audio into written text.
- transcribing podcasts and video audioPodcasts and video · 18th of 92
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 37th of 76
95%
Misses roughly one word in 20, averaged over nine English test sets.
744×40th of 74
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
30
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
Which languages ↓ ↑
Chinese · English · Cantonese · Arabic · German · French · Spanish · Portuguese · Indonesian · Italian · Korean · Russian · Thai · Vietnamese · Japanese · Turkish · Hindi · Malay · Dutch · Swedish · Danish · Finnish · Polish · Czech · Filipino · Persian · Greek · Hungarian · Macedonian · Romanian
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 20.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.1 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.1 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Qwen3 ASR 0.6B HF loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
Models people weigh against Qwen3 ASR 0.6B HF
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen3-ASR-0.6B-hf
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- qwen-qwen3-asr-0-6b-hf