← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized

M4 Pro (20c) · 64 GB · 4bit · 2026-05-09
Performance
1k
tokens
123.3
PP tok/s
12.7
TG tok/s
8308
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 15.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.3 12.7 19.6 GB current
4k 125.7 12.3 21.1 GB view
Batching Results
Batch Size TG tok/s Speedup
12.7 1.00×
23.8 1.87×
29.5 2.32×