← Back to community benchmarks

Qwen3.6-27B-Uncensored-Heretic-v2

M5 Max (40c) · 64 GB · 6bit · 2026-06-19
Performance
32k
tokens
641.6
PP tok/s
22.0
TG tok/s
51069
TTFT (ms)
27.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 715.9 24.5 22.1 GB view
4k 852.6 23.7 23.5 GB view
8k 775.5 24.1 24.2 GB view
16k 700.2 23.4 25.4 GB view
32k 641.6 22.0 27.9 GB current
64k 557.7 19.4 32.9 GB view
128k 421.9 16.5 40.7 GB view
Batching Results
Batch Size TG tok/s Speedup
24.5 1.00×
36.9 1.51×
92.9 3.79×