← Back to community benchmarks

Ornith-1.0-35B

M5 Max (40c) · 128 GB · 8bit · 2026-07-17
Performance
4k
tokens
4,465
PP tok/s
92.8
TG tok/s
917
TTFT (ms)
36.2
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,221 86.6 35.4 GB view
4k 4,465 92.8 36.2 GB current
8k 4,261 83.3 36.6 GB view
16k 4,022 87.5 37.4 GB view
32k 3,318 82.0 39.3 GB view
64k 2,326 70.6 41.8 GB view
Batching Results
Batch Size TG tok/s Speedup
86.6 1.00×
162.0 1.87×
247.5 2.86×
360.6 4.16×