← Back to community benchmarks
MiniMax
Performance
1k
tokens
298.8
PP tok/s
41.7
TG tok/s
3428
TTFT (ms)
94.1
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
128 GB
GPU Cores
76
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 298.8 | 41.7 | 94.1 GB | current |
| 4k | 337.3 | 35.4 | 95.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.7 | 1.00× |
| 2× | 59.7 | 1.43× |
| 4× | 77.0 | 1.85× |