← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M5 Pro (16c) · 48 GB · 4bit · 2026-04-07
Performance
8k
tokens
1,887
PP tok/s
62.3
TG tok/s
4340
TTFT (ms)
11.9
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.4
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,817 69.5 11.8 GB view
8k 1,887 62.3 11.9 GB current