← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (60c) · 256 GB · 4bit · 2026-06-22
Performance
1k
tokens
314.0
PP tok/s
32.7
TG tok/s
3261
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.4.2rc1
macOS macOS 15.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 314.0 32.7 15.8 GB current
4k 320.8 31.6 17.3 GB view
Batching Results
Batch Size TG tok/s Speedup
32.7 1.00×
52.6 1.61×
60.3 1.84×