← Back to community benchmarks

Ornith-1.0-35B-OptiQ

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-21

Performance

8k

tokens

2,130

PP tok/s

81.5

TG tok/s

3846

TTFT (ms)

22.6

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,155	78.1	21.7 GB	view
4k	2,272	77.6	22.5 GB	view
8k	2,130	81.5	22.6 GB	current
16k	1,910	70.8	22.9 GB	view
32k	1,624	65.8	23.1 GB	view
64k	1,207	58.8	23.8 GB	view