← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (30c) · 36 GB · 4bit · 2026-05-18
Performance
16k
tokens
144.1
PP tok/s
20.2
TG tok/s
113660
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384