← Back to community benchmarks
gpt-oss-120b-MXFP4-Q8
Performance
1k
tokens
650.2
PP tok/s
75.3
TG tok/s
1575
TTFT (ms)
59.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 650.2 | 75.3 | 59.5 GB | current |
| 4k | 833.4 | 71.7 | 59.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.3 | 1.00× |
| 2× | 105.4 | 1.40× |
| 4× | 133.1 | 1.77× |