← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Pro (20c) · 64 GB · 8bit · 2026-05-09
Performance
1k
tokens
121.5
PP tok/s
8.6
TG tok/s
8431
TTFT (ms)
28.3
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 121.5 8.6 28.3 GB current
4k 118.9 8.4 29.8 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 8.6 1.00×
2× 16.4 1.91×
4× 21.9 2.55×