← Back to community benchmarks

Qwen3.6-35B-A3B-OptiQ

M3 Ultra (80c) · 96 GB · 4bit · 2026-07-12
Performance
32k
tokens
2,112
PP tok/s
77.2
TG tok/s
15518
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 96 GB
GPU Cores 80
Software
oMLX v0.5.0
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 2,112 77.2 23.0 GB current
64k 1,609 68.2 24.1 GB view
128k 1,087 57.3 25.3 GB view