← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 128 GB · 4bit · 2026-05-13
Performance
16k
tokens
207.1
PP tok/s
32.4
TG tok/s
79106
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.3.1
Context 16,384