← Back to community benchmarks

MiniMax-M2.5

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-15
Performance
4k
tokens
550.7
PP tok/s
34.7
TG tok/s
7437
TTFT (ms)
175.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 477.0 40.4 174.0 GB view
4k 550.7 34.7 175.0 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 40.4 1.00×
2× 56.5 1.40×
4× 71.9 1.78×