← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 64 GB · 4bit · 2026-05-23
Performance
8k
tokens
442.7
PP tok/s
24.8
TG tok/s
18504
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 428.8 26.2 16.8 GB view
4k 466.7 25.8 18.2 GB view
8k 442.7 24.8 19.2 GB current
Batching Results
Batch Size TG tok/s Speedup
26.2 1.00×
30.4 1.16×
38.2 1.46×