MiniMax
MiniMax
/MiniMax M2.7

Quantizations

QuantQuantized bySizeDecodePrefillScoreActions
MLX Community
MLX Community
173.1 GB36.8 tok/s576.6 tok/sRuns poorly

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.

Decode / Prefill Speeds

1 device