← Back to community benchmarks

Qwen3.6-27B-UD

M5 Max (40c) · 64 GB · 4bit · 2026-04-25
Performance
1k
tokens
789.2
PP tok/s
21.4
TG tok/s
1298
TTFT (ms)
25.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 789.2 21.4 25.2 GB current
4k 826.6 21.0 26.6 GB view
8k 727.2 20.1 27.3 GB view
16k 670.8 19.2 28.5 GB view
32k 556.9 13.0 31.0 GB view
Batching Results
Batch Size TG tok/s Speedup
21.4 1.00×
16.2 0.76×
23.8 1.11×