← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M5 Pro (20c) · 64 GB · 4bit · 2026-07-01
Performance
16k
tokens
2,220
PP tok/s
71.3
TG tok/s
7381
TTFT (ms)
12.3
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 2,137 79.4 11.9 GB view
16k 2,220 71.3 12.3 GB current
64k 1,568 43.9 14.0 GB view