← Back to community benchmarks

Ornith-1.0-35B-OptiQ

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

Performance

64k

tokens

1,207

PP tok/s

58.8

TG tok/s

54282

TTFT (ms)

23.8

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 65,536

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	view
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	current