← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 48 GB · 8bit · 2026-05-18
Performance
4k
tokens
243.4
PP tok/s
16.3
TG tok/s
16831
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096