← Back to community benchmarks
MiniMax-M2.1
Performance
64k
tokens
296.7
PP tok/s
11.6
TG tok/s
220896
TTFT (ms)
136.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 664.5 | 47.0 | 120.7 GB | view |
| 4k | 752.6 | 40.5 | 121.7 GB | view |
| 8k | 696.4 | 33.7 | 122.6 GB | view |
| 16k | 589.0 | 26.7 | 124.6 GB | view |
| 32k | 438.1 | 17.6 | 128.5 GB | view |
| 64k | 296.7 | 11.6 | 136.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.0 | 1.00× |
| 2× | 71.1 | 1.51× |
| 4× | 101.0 | 2.15× |
| 8× | 137.0 | 2.91× |