← Back to community benchmarks
gpt-oss-120b-RotorQuant
Performance
8k
tokens
1,450
PP tok/s
79.5
TG tok/s
5651
TTFT (ms)
58.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,239 | 92.6 | 58.4 GB | view |
| 4k | 1,643 | 86.2 | 58.5 GB | view |
| 8k | 1,450 | 79.5 | 58.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 92.6 | 1.00× |
| 2× | 124.5 | 1.34× |
| 4× | 150.8 | 1.63× |