← Back to community benchmarks

Qwen3.6-27B-5bit

M4 Max (40c) · 48 GB · 5bit · 2026-07-12
Performance
64k
tokens
190.9
PP tok/s
18.6
TG tok/s
343353
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 221.0 21.4 24.8 GB view
64k 190.9 18.6 25.4 GB current