← Back to community benchmarks
MiniMax-M2.5
Performance
8k
tokens
326.9
PP tok/s
30.2
TG tok/s
25058
TTFT (ms)
122.6
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 300.1 | 42.1 | 120.7 GB | view |
| 4k | 342.0 | 36.1 | 121.7 GB | view |
| 8k | 326.9 | 30.2 | 122.6 GB | current |
| 16k | 287.2 | 23.0 | 124.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.1 | 1.00× |
| 2× | 62.5 | 1.48× |
| 4× | 80.9 | 1.92× |