← Back to community benchmarks
MiniMax-M2.5
Performance
4k
tokens
579.7
PP tok/s
40.5
TG tok/s
7066
TTFT (ms)
121.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 527.6 | 48.0 | 120.7 GB | view |
| 4k | 579.7 | 40.5 | 121.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.0 | 1.00× |
| 2× | 71.6 | 1.49× |
| 4× | 99.0 | 2.06× |
| 8× | 127.0 | 2.65× |