← Back to community benchmarks

Qwen3___6-27B

M3 Ultra (80c) · 256 GB · 6bit · 2026-06-17
Performance
8k
tokens
412.2
PP tok/s
28.7
TG tok/s
19876
TTFT (ms)
24.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 256 GB
GPU Cores 80
Software
oMLX v0.4.4
macOS macOS 15.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 383.6 29.6 22.1 GB view
4k 413.0 29.3 23.5 GB view
8k 412.2 28.7 24.2 GB current
16k 401.6 27.8 25.4 GB view
Batching Results
Batch Size TG tok/s Speedup
29.6 1.00×
48.0 1.62×