← Back to community benchmarks

community--Qwen3.6-27B

M3 (10c) · 24 GB · 4bit · 2026-06-19
Performance
1k
tokens
46.2
PP tok/s
3.8
TG tok/s
22155
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 46.2 3.8 15.8 GB current
4k 46.2 4.5 17.2 GB view
Batching Results
Batch Size TG tok/s Speedup
3.8 1.00×
9.9 2.61×
13.2 3.47×