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 rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GTX 1060 3GB4-bit9.9 tok/sreported18,068- GB2,048llama.cpp
GTX 1060 3GB ×24-bit18.3 tok/sreported-1.2 GB2,048llama.cpp
RTX 3060 12GB4-bit225.7 tok/smeasured513- GB131,072llama.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.