← Back to community benchmarks
MiniMax-M2___5
Performance
4k
tokens
724.9
PP tok/s
31.8
TG tok/s
5650
TTFT (ms)
228.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 621.7 | 35.9 | 227.2 GB | view |
| 4k | 724.9 | 31.8 | 228.2 GB | current |
| 8k | 675.2 | 28.2 | 229.1 GB | view |
| 16k | 574.9 | 23.2 | 231.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.9 | 1.00× |
| 2× | 51.2 | 1.43× |
| 4× | 64.6 | 1.80× |