← Back to community benchmarks

Qwen3.6-27B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-06-17
Performance
16k
tokens
441.0
PP tok/s
13.3
TG tok/s
37156
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.3
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 292.1 13.9 25.2 GB view
4k 429.8 13.9 26.6 GB view
8k 458.3 13.7 27.3 GB view
16k 441.0 13.3 28.5 GB current
Batching Results
Batch Size TG tok/s Speedup
13.9 1.00×
12.9 0.93×
21.6 1.55×