← Back to community benchmarks

Qwen3.6-27B-mtp

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-21
Performance
4k
tokens
319.6
PP tok/s
22.3
TG tok/s
12815
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 299.2 22.8 28.3 GB view
4k 319.6 22.3 29.8 GB current
Batching Results
Batch Size TG tok/s Speedup
22.8 1.00×
39.1 1.71×