← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 64 GB · 4bit · 2026-05-07
Performance
128k
tokens
74.7
PP tok/s
10.6
TG tok/s
1754645
TTFT (ms)
42.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 113.4 20.5 16.8 GB view
4k 100.8 18.7 18.2 GB view
64k 91.6 14.0 27.6 GB view
128k 74.7 10.6 42.1 GB current
Batching Results
Batch Size TG tok/s Speedup
20.5 1.00×
23.5 1.15×
27.8 1.36×