Qwen3-ASR-1.7B-hf
The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. The 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial A...
Params
2.0 B
Context
—
Downloads 30d
376 K
Likes
140
Download history
daily snapshots · 26 days376 K337 K
Sep 30Oct 8Oct 17Oct 25
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 4.1 GB | 5.3 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3ASRForConditionalGeneration
- Parameters
- 2.0 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-06-26
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-30
Compare with any automatic-speech-recognition model