← Back to community benchmarks

Qwen3.6-27B-OptiQ

M4 Max (40c) · 48 GB · 4bit · 2026-06-19
Performance
4k
tokens
251.9
PP tok/s
24.1
TG tok/s
16257
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 240.9 25.0 19.2 GB view
4k 251.9 24.1 20.6 GB current
Batching Results
Batch Size TG tok/s Speedup
25.0 1.00×
46.3 1.85×
93.3 3.73×