← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-13
Performance
32k
tokens
84.7
PP tok/s
14.6
TG tok/s
386728
TTFT (ms)
22.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 84.7 14.6 22.6 GB current
64k 76.8 11.5 29.8 GB view