← Back to community benchmarks

gpt-oss-120b-MXFP4-Q8

M4 Max (40c) · 128 GB · 4bit · 2026-04-17

Performance

1k

tokens

699.3

PP tok/s

74.1

TG tok/s

1464

TTFT (ms)

59.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 15.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	699.3	74.1	59.5 GB	current
4k	810.5	69.5	59.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	74.1	1.00×
2×	104.3	1.41×
4×	131.3	1.77×