← Back to community benchmarks

Qwen3.6-27BoQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-27
Performance
32k
tokens
139.2
PP tok/s
13.3
TG tok/s
235407
TTFT (ms)
22.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8.dev1
macOS macOS 26.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 122.7 19.8 16.6 GB view
4k 150.2 18.9 18.1 GB view
8k 151.5 18.6 18.7 GB view
16k 147.4 16.7 19.9 GB view
32k 139.2 13.3 22.4 GB current
Batching Results
Batch Size TG tok/s Speedup
19.8 1.00×
28.8 1.45×