community pool / model answer

LFM2.5-2.6B-OptiQ-4bit

chat · mlx-community/LFM2.5-2.6B-OptiQ-4bit

106.6 tok/s · model median · 0 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines

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.