← Back to community benchmarks
MiniMax-M2.5
Performance
64k
tokens
292.1
PP tok/s
11.5
TG tok/s
224399
TTFT (ms)
136.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.9
macOS
macOS 26.0.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 643.9 | 43.7 | 120.7 GB | view |
| 4k | 745.1 | 37.6 | 121.7 GB | view |
| 8k | 693.4 | 32.4 | 122.6 GB | view |
| 16k | 581.2 | 25.3 | 124.6 GB | view |
| 32k | 170.9 | 0.4 | 128.5 GB | view |
| 64k | 292.1 | 11.5 | 136.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.7 | 1.00× |
| 2× | 67.6 | 1.55× |
| 4× | 98.7 | 2.26× |
| 8× | 143.2 | 3.28× |