← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (20c) · 48 GB · 4bit · 2026-07-22
Performance
8k
tokens
765.5
PP tok/s
60.6
TG tok/s
10702
TTFT (ms)
12.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 791.5 67.3 11.8 GB view
4k 799.4 65.1 11.8 GB view
8k 765.5 60.6 12.0 GB current
16k 701.3 54.6 12.3 GB view
32k 581.8 45.7 12.8 GB view
64k 467.1 34.5 14.0 GB view
128k 332.2 23.8 16.3 GB view
195k 238.2 17.0 19.5 GB view
Batching Results
Batch Size TG tok/s Speedup
67.3 1.00×
97.7 1.45×
123.7 1.84×
138.6 2.06×