← Back to community benchmarks
gpt-oss-120b-MXFP4-Q8
Performance
8k
tokens
365.9
PP tok/s
43.7
TG tok/s
22387
TTFT (ms)
59.5
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
128 GB
GPU Cores
76
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 365.9 | 43.7 | 59.5 GB | current |
| 16k | 361.6 | 38.4 | 59.8 GB | view |