← Back to community benchmarks

Ornith-1.0-35B

M5 Pro (20c) · 64 GB · 4bit · 2026-07-06
Performance
16k
tokens
2,164
PP tok/s
93.3
TG tok/s
7571
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,496 110.2 19.2 GB view
4k 2,216 106.2 20.0 GB view
8k 2,283 101.2 20.5 GB view
16k 2,164 93.3 21.2 GB current
Batching Results
Batch Size TG tok/s Speedup
110.2 1.00×
153.2 1.39×
200.0 1.81×