← Back to community benchmarks
gpt-oss-120b-MXFP4-Q8
Performance
1k
tokens
745.8
PP tok/s
81.3
TG tok/s
1373
TTFT (ms)
59.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 745.8 | 81.3 | 59.5 GB | current |
| 4k | 1,442 | 75.7 | 59.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.3 | 1.00× |
| 2× | 112.3 | 1.38× |
| 4× | 129.6 | 1.59× |