← Back to community benchmarks

Qwen3.6-27B

M5 Pro (16c) · 48 GB · 4bit · 2026-04-26
Performance
4k
tokens
378.5
PP tok/s
17.1
TG tok/s
10822
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 347.8 17.1 15.8 GB view
4k 378.5 17.1 17.3 GB current
16k 347.9 15.5 19.1 GB view
Batching Results
Batch Size TG tok/s Speedup
17.1 1.00×
26.5 1.55×
31.9 1.87×