← Back to community benchmarks
gpt-oss-20b-MXFP4-Q8
Performance
8k
tokens
2,137
PP tok/s
79.4
TG tok/s
3834
TTFT (ms)
11.9
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
8,192