Quantization-specific throughput and VRAM requirements for Qwen/Qwen3-ASR-1.7B running on Intel Arc Pro A40.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 2GB | 6GB | 56 tok/s | ✅ Fits |
| Q8 | 3GB | 6GB | 35 tok/s | ✅ Fits |
| FP16 | 6GB | 6GB | 18 tok/s | ⚠️ Tight fit |