← Back to community benchmarks

MiniMax-M2.5

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-12
Performance
8k
tokens
693.4
PP tok/s
32.4
TG tok/s
11814
TTFT (ms)
122.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.9
macOS macOS 26.0.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 643.9 43.7 120.7 GB view
4k 745.1 37.6 121.7 GB view
8k 693.4 32.4 122.6 GB current
16k 581.2 25.3 124.6 GB view
32k 170.9 0.4 128.5 GB view
64k 292.1 11.5 136.4 GB view
Batching Results
Batch Size TG tok/s Speedup
43.7 1.00×
67.6 1.55×
98.7 2.26×
143.2 3.28×