← Back to community benchmarks
MiniMax-M2.5
Performance
4k
tokens
578.4
PP tok/s
40.6
TG tok/s
7081
TTFT (ms)
121.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 526.4 | 47.9 | 120.7 GB | view |
| 4k | 578.4 | 40.6 | 121.7 GB | current |
| 8k | 532.2 | 33.4 | 122.6 GB | view |
| 16k | 447.9 | 26.9 | 124.6 GB | view |
| 32k | 337.6 | 18.6 | 128.5 GB | view |
| 64k | 221.7 | 11.6 | 136.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.9 | 1.00× |
| 2× | 71.5 | 1.49× |
| 4× | 99.2 | 2.07× |
| 8× | 128.3 | 2.68× |