← Back to community benchmarks

MiniMax-M2.5

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-12
Performance
16k
tokens
581.2
PP tok/s
25.3
TG tok/s
28188
TTFT (ms)
124.6
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 16,384
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 view
16k 581.2 25.3 124.6 GB current
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×