← Back to community benchmarks

Qwen3.6-27B-UD-Q4_K_XL

M5 Max (40c) · 128 GB · 4bit · 2026-06-17
Performance
32k
tokens
630.5
PP tok/s
20.9
TG tok/s
51971
TTFT (ms)
27.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 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
8k 821.6 24.8 23.4 GB view
32k 630.5 20.9 27.8 GB current
128k 340.8 11.6 44.7 GB view