community pool / model answer

gemma-4-26B-A4B-it-QAT-MLX-4bit

chat · lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M4 Pro 48GB4-bit65.4 tok/sreported-15.7 GB2,176mlx

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.