← Back to community benchmarks
MiniMax-M2.5
Performance
64k
tokens
289.0
PP tok/s
9.8
TG tok/s
226775
TTFT (ms)
242.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 616.8 | 35.5 | 227.2 GB | view |
| 4k | 724.3 | 31.4 | 228.2 GB | view |
| 8k | 674.2 | 27.2 | 229.1 GB | view |
| 16k | 574.9 | 22.2 | 231.1 GB | view |
| 32k | 437.0 | 15.8 | 235.0 GB | view |
| 64k | 289.0 | 9.8 | 242.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.5 | 1.00× |
| 2× | 50.4 | 1.42× |
| 4× | 68.2 | 1.92× |