← Back to community benchmarks
gpt-oss-120b-MXFP4-Q8
Performance
4k
tokens
852.0
PP tok/s
67.9
TG tok/s
4808
TTFT (ms)
59.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
4,096