← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Quality

M4 Max (40c) · 64 GB · 4bit · 2026-05-23
Performance
4k
tokens
197.3
PP tok/s
15.3
TG tok/s
20757
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 219.9 16.2 28.3 GB view
4k 197.3 15.3 29.8 GB current
8k 195.7 14.9 30.8 GB view
Batching Results
Batch Size TG tok/s Speedup
16.2 1.00×
27.1 1.67×
34.0 2.10×