← Back to community benchmarks
MiniMax-M2.7
Performance
16k
tokens
453.9
PP tok/s
22.1
TG tok/s
36093
TTFT (ms)
177.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 499.0 | 40.7 | 174.0 GB | view |
| 4k | 578.6 | 34.1 | 175.0 GB | view |
| 8k | 536.0 | 28.5 | 175.8 GB | view |
| 16k | 453.9 | 22.1 | 177.8 GB | current |
| 32k | 341.7 | 15.1 | 181.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.7 | 1.00× |
| 2× | 57.6 | 1.42× |
| 4× | 73.4 | 1.80× |