← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-18
Performance
4k
tokens
318.7
PP tok/s
32.2
TG tok/s
12854
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 298.5 30.7 28.8 GB view
4k 318.7 32.2 30.3 GB current
Batching Results
Batch Size TG tok/s Speedup
30.7 1.00×
39.8 1.30×
50.3 1.64×