← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (16c) · 48 GB · 4bit · 2026-05-18
Performance
1k
tokens
99.5
PP tok/s
14.9
TG tok/s
10288
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 99.5 14.9 16.4 GB current
4k 100.3 14.5 17.9 GB view
8k 98.5 13.9 18.5 GB view
16k 95.9 13.4 19.8 GB view
Batching Results
Batch Size TG tok/s Speedup
14.9 1.00×
22.7 1.52×
45.5 3.05×