← Back to community benchmarks

MiniMax-M2.5-mixed-2

M4 Max (40c) · 128 GB · 4bit · 2026-03-11
Performance
16k
tokens
315.6
PP tok/s
26.2
TG tok/s
51921
TTFT (ms)
98.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 410.1 50.2 94.7 GB view
4k 432.8 41.8 95.7 GB view
8k 366.4 34.6 96.6 GB view
16k 315.6 26.2 98.6 GB current
Batching Results
Batch Size TG tok/s Speedup
50.2 1.00×
67.2 1.34×
79.6 1.59×
90.1 1.79×