Quantization-specific throughput and VRAM requirements for lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit running on NVIDIA H100 SXM5 80GB.
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 | 4GB | 80GB | 499 tok/s | ✅ Fits |
| Q8 | 9GB | 80GB | 363 tok/s | ✅ Fits |
| FP16 | 17GB | 80GB | 201 tok/s | ✅ Fits |