← Back to community benchmarks

Qwen3.6-27B

M1 Max (24c) · 32 GB · 4bit · 2026-06-04
Performance
32k
tokens
35.1
PP tok/s
10.4
TG tok/s
934850
TTFT (ms)
21.9
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.4.2.dev2
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 66.1 13.7 15.5 GB view
4k 65.4 12.4 16.6 GB view
16k 65.9 11.7 19.8 GB view
32k 35.1 10.4 21.9 GB current
Batching Results
Batch Size TG tok/s Speedup
13.7 1.00×
15.7 1.15×
17.4 1.27×