← Back to community benchmarks

Ornith-1.0-35B-oQ4e

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

Performance

64k

tokens

1,629

PP tok/s

60.3

TG tok/s

40241

TTFT (ms)

25.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	1,629	60.3	25.6 GB	current
128k	886.3	37.7	31.1 GB	view