← Back to community benchmarks

Qwen3.6-27B-OptiQ

M4 Max (40c) · 48 GB · 4bit · 2026-06-17
Performance
4k
tokens
226.8
PP tok/s
23.6
TG tok/s
18062
TTFT (ms)
20.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 237.2 24.9 19.2 GB view
4k 226.8 23.6 20.6 GB current
8k 212.7 23.1 21.3 GB view
Batching Results
Batch Size TG tok/s Speedup
24.9 1.00×
38.9 1.56×