← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 48 GB · 4bit · 2026-05-21
Performance
1k
tokens
123.1
PP tok/s
23.4
TG tok/s
8320
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 123.1 23.4 16.7 GB current
4k 121.2 21.8 18.2 GB view
8k 113.9 20.0 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
23.4 1.00×
25.4 1.09×
28.5 1.22×