← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-18
Performance
1k
tokens
306.2
PP tok/s
39.3
TG tok/s
3345
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 306.2 39.3 15.8 GB current
4k 323.3 37.7 17.3 GB view
32k 295.0 31.1 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
39.3 1.00×
63.3 1.61×
72.3 1.84×