← Back to community benchmarks
MiniMax-M2.7-5bit
Performance
4k
tokens
265.3
PP tok/s
29.1
TG tok/s
15438
TTFT (ms)
148.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
192 GB
GPU Cores
60
Software
oMLX
v0.3.5.dev1
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 227.8 | 35.3 | 147.3 GB | view |
| 4k | 265.3 | 29.1 | 148.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.3 | 1.00× |
| 2× | 48.2 | 1.37× |
| 4× | 58.4 | 1.65× |