community pool / model answer

LFM2-700M

chat · LiquidAI/LFM2-700M

92.1 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
AMD Ryzen 7 7840HS4-bit113.9 tok/sreported-- GB2,048llama.cpp
AMD Ryzen 7 7840HS8-bit70.3 tok/sreported-- GB2,048llama.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.