← Back to community benchmarks

Qwen:Qwen3.6-27B-oQ8

M2 Max (38c) · 96 GB · 8bit · 2026-04-30
Performance
1k
tokens
168.1
PP tok/s
68.4
TG tok/s
6092
TTFT (ms)
30.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 1,024