← Back to community benchmarks

Ornith-1.0-35B

M5 Max (40c) · 128 GB · 8bit · 2026-07-18
Performance
8k
tokens
4,441
PP tok/s
91.5
TG tok/s
1845
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,447 93.6 35.4 GB view
4k 4,529 92.5 36.2 GB view
8k 4,441 91.5 36.7 GB current
16k 4,093 87.0 37.6 GB view
32k 3,392 81.3 39.4 GB view
64k 2,399 70.6 42.1 GB view
Batching Results
Batch Size TG tok/s Speedup
93.6 1.00×
162.3 1.73×
248.9 2.66×
359.5 3.84×