← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 64 GB · 4bit · 2026-05-07
Performance
1k
tokens
113.4
PP tok/s
20.5
TG tok/s
9031
TTFT (ms)
16.8
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 113.4 20.5 16.8 GB current
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 view
Batching Results
Batch Size TG tok/s Speedup
20.5 1.00×
23.5 1.15×
27.8 1.36×