← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-18
Performance
32k
tokens
295.0
PP tok/s
31.1
TG tok/s
111084
TTFT (ms)
21.6
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 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 306.2 39.3 15.8 GB view
4k 323.3 37.7 17.3 GB view
32k 295.0 31.1 21.6 GB current
Batching Results
Batch Size TG tok/s Speedup
39.3 1.00×
63.3 1.61×
72.3 1.84×