community pool / model answer

Laguna-S-2.1-MLX-4bit

chat · pipenetwork/Laguna-S-2.1-MLX-4bit

63.8 tok/s · model median · 5 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Max 128GB4-bit63.8 tok/smeasured1,71066 GB1,800mlx

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.