← Back to community benchmarks

Qwen3.6-27B

M5 (10c) · 32 GB · 4bit · 2026-05-20
Performance
1k
tokens
192.4
PP tok/s
8.8
TG tok/s
5322
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 192.4 8.8 15.0 GB current
4k 192.4 8.5 16.4 GB view
8k 173.8 8.2 17.0 GB view
16k 128.7 6.8 18.3 GB view
Batching Results
Batch Size TG tok/s Speedup
8.8 1.00×
13.8 1.57×
27.8 3.16×