← Back to community benchmarks

Ornith-1.0-35B-oQ4e

M5 Max (40c) · 128 GB · 4bit · 2026-07-13

Performance

16k

tokens

2,094

PP tok/s

80.5

TG tok/s

7825

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,338	100.5	20.7 GB	view
16k	2,094	80.5	21.9 GB	current
64k	1,359	59.8	26.0 GB	view