← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 24 GB · 4bit · 2026-05-03
Performance
32k
tokens
312.2
PP tok/s
14.4
TG tok/s
104954
TTFT (ms)
12.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 393.3 32.7 11.8 GB view
32k 312.2 14.4 12.4 GB current