community pool / model answer
LFM2-8B-A1B
chat · LiquidAI/LFM2-8B-A1B
210.8 tok/s · model median · 24 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GTX 1060 3GB | 4-bit | 9.9 tok/s | reported | 18,068 | - GB | 2,048 | llama.cpp |
| GTX 1060 3GB ×2 | 4-bit | 18.3 tok/s | reported | - | 1.2 GB | 2,048 | llama.cpp |
| RTX 3060 12GB | 4-bit | 225.7 tok/s | measured | 513 | - GB | 131,072 | 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.