Quantization-specific throughput and VRAM requirements for google/gemma-2-27b-it running on AMD Instinct MI300X.
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 | 14GB | 192GB | 449 tok/s | ✅ Fits |
| Q8 | 28GB | 192GB | 296 tok/s | ✅ Fits |
| FP16 | 56GB | 192GB | 171 tok/s | ✅ Fits |