← Back to community benchmarks
MiniMax-M2.5
Performance
1k
tokens
465.6
PP tok/s
24.4
TG tok/s
2199
TTFT (ms)
426.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 465.6 | 24.4 | 426.9 GB | current |
| 4k | 637.5 | 20.9 | 427.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.4 | 1.00× |
| 2× | 26.2 | 1.07× |
| 4× | 33.8 | 1.39× |