← Back to community benchmarks

Qwen3.6-27B-UD

M1 Max (32c) · 64 GB · 6bit · 2026-04-24
Performance
8k
tokens
96.4
PP tok/s
10.3
TG tok/s
84976
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 15.7.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 94.2 10.8 29.2 GB view
4k 96.9 10.5 30.6 GB view
8k 96.4 10.3 31.3 GB current
Batching Results
Batch Size TG tok/s Speedup
10.8 1.00×
21.7 2.01×
43.4 4.02×
77.8 7.20×