community pool / model answer

LFM2-8B-A1B-GGUF

chat · unsloth/LFM2-8B-A1B-GGUF

231.4 tok/s · model median · 8 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit231.4 tok/smeasured9006.4 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.