Alibaba (Qwen) · Apache 2.0
Qwen3-ASR
Alibaba’s speech recognition for 30 languages and 22 Chinese dialects, in 1.7B and 0.6B sizes.
How much memory it needs
Memory to run each model, from its model card or the size of its files. Smaller versions trade some quality for less memory.
| Model | Version | Needs | Business use |
|---|---|---|---|
| Qwen3-ASR 1.7B | Smaller 0.6B model | 1.9 GB | Allowed |
| BF16 | 4.7 GB |
Which computers run it
The best model in this group for each machine.
| Computer | Best version | Fit |
|---|---|---|
| Laptop or PC, no graphics card, 32 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX 4060 · 8 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX 3060 · 12 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX 5060 Ti · 16 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX 4090 · 24 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX 5090 · 32 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Mac with M4 · 16 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Mac with M4 Pro · 48 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Mac with M5 Max · 128 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Ryzen AI Max+ 395 · 128 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| DGX Spark · 128 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| RTX PRO 6000 · 96 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Mac Studio with M5 Ultra · 256 GB | Qwen3-ASR 1.7B BF16 | Runs great |
| Mac Studio with M3 Ultra · 512 GB | Qwen3-ASR 1.7B BF16 | Runs great |
What it is good and bad at
Good at
- Many languages and dialects
Not good at
- Needs Transformers or vLLM, not a one-click app
Start it
- Qwen3-ASR 1.7B: runs in qwen-asr (Transformers / vLLM) (also Transformers (native support since 2026-06-26)). Model card