← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (24c) · 32 GB · 4bit · 2026-05-09
Performance
1k
tokens
67.0
PP tok/s
14.2
TG tok/s
15274
TTFT (ms)
16.8
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.9.dev1
macOS macOS 26.4
Context 1,024