← Back to community benchmarks

Ornstein-Hermes-3.6-27B-SABER-4bit-MTPLX-Optimized-Speed

M5 Max (40c) · 64 GB · 4bit · 2026-05-24
Performance
1k
tokens
795.0
PP tok/s
32.9
TG tok/s
1288
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 1,024