← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (60c) · 256 GB · 4bit · 2026-04-26
Performance
1k
tokens
303.8
PP tok/s
38.3
TG tok/s
3371
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.6
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 303.8 38.3 15.8 GB current
4k 320.7 37.0 17.3 GB view
8k 318.8 34.9 17.9 GB view
32k 292.2 25.5 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
38.3 1.00×
65.0 1.70×
77.1 2.01×