← Back to community benchmarks
MiniMax-M2.7
Performance
16k
tokens
596.4
PP tok/s
28.9
TG tok/s
27470
TTFT (ms)
187.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 636.3 | 40.9 | 181.2 GB | view |
| 4k | 754.1 | 37.4 | 182.5 GB | view |
| 8k | 701.5 | 33.4 | 184.1 GB | view |
| 16k | 596.4 | 28.9 | 187.1 GB | current |
| 32k | 453.2 | 22.1 | 192.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.9 | 1.00× |
| 2× | 81.6 | 2.00× |
| 4× | 162.5 | 3.97× |
| 8× | 325.4 | 7.96× |