community pool / model answer
LFM2-350M
chat · LiquidAI/LFM2-350M
231.6 tok/s · model median · 34 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| AMD Ryzen 7 7840HS | 2-bit | 296.1 tok/s | measured | - | - GB | 512 | llama.cpp |
| AMD Ryzen 7 7840HS | 4-bit | 219.3 tok/s | measured | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 8-bit | 142.1 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| RTX 3060 12GB | 8-bit | 574.5 tok/s | reported | 140 | 1.9 GB | 4,608 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.