community pool / model answer

LFM2.5-1.2B-Instruct-GGUF

chat · lmstudio-community/LFM2.5-1.2B-Instruct-GGUF

186 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Pro 24GB8-bit186 tok/sreported88- GB4,224llama.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.