community pool / model answer

DeepSeek-V4-Flash-2bit-DQ

chat · mlx-community/DeepSeek-V4-Flash-2bit-DQ

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Max 128GB2-bit17 tok/sreported-- GB2,048mlx

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.