Loading content...
Loading GPU benchmarks...
AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of LiquidAI/LFM2-1.2B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 1GB | 192GB | 884.14 tok/s | ✅ Fits comfortably |
| Q8 | 2GB | 192GB | 581.26 tok/s | ✅ Fits comfortably |
| FP16 | 4GB | 192GB | 347.74 tok/s | ✅ Fits comfortably |