← Back to community benchmarks

gpt-oss-20b

M1 Max (24c) · 64 GB · 8bit · 2026-03-09

Performance

4k

tokens

276.0

PP tok/s

46.2

TG tok/s

14838

TTFT (ms)

20.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.2.6

macOS macOS 15.7.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	246.3	50.8	20.9 GB	view
4k	276.0	46.2	20.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.8	1.00×
2×	63.1	1.24×
4×	73.1	1.44×