← Back to community benchmarks

Ornith-1.0-35B-5bit

M5 Pro (20c) · 64 GB · 5bit · 2026-07-05

Performance

1k

tokens

1,198

PP tok/s

70.4

TG tok/s

855

TTFT (ms)

24.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 27.0

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,198	70.4	24.1 GB	current
4k	1,682	70.0	24.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	70.4	1.00×
2×	113.2	1.61×
4×	155.2	2.20×