← Back to community benchmarks
MiniMax-M2.5
Performance
1k
tokens
511.0
PP tok/s
24.3
TG tok/s
2004
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 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 511.0 | 24.3 | 426.9 GB | current |
| 4k | 689.0 | 22.5 | 427.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.3 | 1.00× |
| 2× | 29.1 | 1.20× |