← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (16c) · 24 GB · 4bit · 2026-03-19
Performance
64k
tokens
373.5
PP tok/s
21.1
TG tok/s
175442
TTFT (ms)
13.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.19
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 583.4 67.3 11.7 GB view
4k 643.7 61.0 11.8 GB view
64k 373.5 21.1 13.3 GB current
Batching Results
Batch Size TG tok/s Speedup
67.3 1.00×
89.9 1.34×
101.2 1.50×