← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 32 GB · 4bit · 2026-03-10

Performance

1k

tokens

303.4

PP tok/s

33.5

TG tok/s

3375

TTFT (ms)

11.4

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	303.4	33.5	11.4 GB	current
4k	316.1	29.9	11.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.5	1.00×
2×	43.7	1.30×
4×	53.5	1.60×