← Back to community benchmarks

gpt-oss-120b-MXFP4-Q8

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-14

Performance

1k

tokens

595.6

PP tok/s

76.3

TG tok/s

1719

TTFT (ms)

59.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	595.6	76.3	59.2 GB	current
4k	717.9	61.3	59.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	76.3	1.00×
2×	110.2	1.44×
4×	150.1	1.97×