← Back to community benchmarks

Ornith-1.0-35BVL-oQ6

M1 Max (24c) · 64 GB · 6bit · 2026-07-12
Performance
32k
tokens
532.3
PP tok/s
40.1
TG tok/s
61560
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.5.0
macOS macOS 27.0
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 733.2 47.4 27.8 GB view
16k 645.8 43.3 28.8 GB view
32k 532.3 40.1 29.4 GB current
64k 393.6 33.0 30.3 GB view
Batching Results
Batch Size TG tok/s Speedup
47.4 1.00×
70.7 1.49×