← Back to community benchmarks

Ornith-1.0-35B-oQ4

M1 Max (32c) · 64 GB · 4bit · 2026-07-19

Performance

32k

tokens

410.5

PP tok/s

45.7

TG tok/s

79823

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.5.1

macOS macOS 26.5.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	410.5	45.7	21.2 GB	current
64k	292.8	37.9	22.1 GB	view
128k	193.6	31.0	23.3 GB	view
195k	143.3	23.8	24.8 GB	view