LFM2-350M
LFM family · 0.3B params
1recorded run
2231.4best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 50902231.4
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| RTX 5090 · 32 GB | LFM2-350M | NVFP4 | sglang unknown | 704 | 2231.4 ✓ | — | 28.4 | src |