← Back to community benchmarks
gpt-oss-120b-MXFP4-Q8
Performance
32k
tokens
1,368
PP tok/s
39.0
TG tok/s
23958
TTFT (ms)
60.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
32,768