← Back to community benchmarks

gpt-oss-20b-MXFP4-Q4

M5 (10c) · 32 GB · 4bit · 2026-05-12
Performance
4k
tokens
1,110
PP tok/s
50.2
TG tok/s
3690
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 916.3 53.9 10.8 GB view
4k 1,110 50.2 10.9 GB current