← Back to community benchmarks

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

M4 Pro (16c) · 24 GB · 4bit · 2026-05-22
Performance
4k
tokens
101.8
PP tok/s
15.2
TG tok/s
40228
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.9
macOS macOS 26.5
Context 4,096