§01·model · /models

Qwen3.5 35B

multimodalactiveApache-2.0

35B Mixture-of-Experts LLM by Alibaba (Qwen3.5-35B-A3B, ~3B active per token). Apache-2.0.

§02·GPUs that run this model

2 total

GPU	VRAM	Series	Best speed	Min VRAM	Works	Benchmarks	Recipe
RTX 5090	32GB	50	165.2tokens/s		✓	2	recipe	check ↗
RTX 3090	24GB	30	111.2tokens/s	24GB	✓	2	recipe	check ↗

✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit