Quantization-specific throughput and VRAM requirements for GSAI-ML/LLaDA-8B-Base running on AMD Instinct MI210.
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 | 64GB | 259 tok/s | ✅ Fits |
| Q8 | 9GB | 64GB | 173 tok/s | ✅ Fits |
| FP16 | 17GB | 64GB | 91 tok/s | ✅ Fits |