← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-18
Performance
1k
tokens
363.0
PP tok/s
41.6
TG tok/s
2821
TTFT (ms)
24.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.9.dev2
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 363.0 41.6 24.2 GB current
4k 392.5 41.9 25.6 GB view
8k 393.8 39.5 26.7 GB view
Batching Results
Batch Size TG tok/s Speedup
41.6 1.00×
58.3 1.40×
78.3 1.88×
88.1 2.12×