← Back to community benchmarks

Qwen3.6-27B-UD

M4 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
8k
tokens
209.0
PP tok/s
16.6
TG tok/s
39204
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 245.8 18.7 25.2 GB view
4k 225.2 17.5 26.6 GB view
8k 209.0 16.6 27.6 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 18.7 1.00×
2× 18.9 1.01×
4× 30.0 1.60×