← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (40c) · 64 GB · 4bit · 2026-06-05
Performance
32k
tokens
152.3
PP tok/s
14.9
TG tok/s
215136
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 15.7.7
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 195.4 26.9 20.1 GB view
32k 152.3 14.9 23.7 GB current
64k 126.4 13.0 29.8 GB view