← Back to community benchmarks

MiniMax-M2.7-REAP-172B-A10B

M3 Ultra (60c) · 256 GB · 4bit · 2026-05-01
Performance
4k
tokens
617.0
PP tok/s
40.6
TG tok/s
6638
TTFT (ms)
92.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 554.4 47.6 91.3 GB view
4k 617.0 40.6 92.3 GB current
Batching Results
Batch Size TG tok/s Speedup
47.6 1.00×
72.1 1.51×
98.6 2.07×