← Back to community benchmarks

Ornith-1.0-35B-MTPLX

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-23

Performance

4k

tokens

2,295

PP tok/s

101.4

TG tok/s

1785

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,212	105.2	19.4 GB	view
4k	2,295	101.4	20.1 GB	current
8k	2,189	96.0	20.2 GB	view
16k	1,966	91.2	20.3 GB	view
32k	1,632	84.6	20.7 GB	view
64k	1,231	71.6	21.5 GB	view