community pool / model answer

LFM2-350M

chat · LiquidAI/LFM2-350M

231.6 tok/s · model median · 34 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
AMD Ryzen 7 7840HS2-bit296.1 tok/smeasured-- GB512llama.cpp
AMD Ryzen 7 7840HS4-bit219.3 tok/smeasured-- GB2,048llama.cpp
AMD Ryzen 7 7840HS8-bit142.1 tok/sreported-- GB2,048llama.cpp
RTX 3060 12GB8-bit574.5 tok/sreported1401.9 GB4,608llama.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.