[simonw]

For this particular model, yes.

This new one from Qwen should fit though - it looks like that only needs ~30GB of RAM: https://huggingface.co/lmstudio-community/Qwen3-30B-A3B-Inst...

[omneity]

It takes ~17-20GB on Q4 depending on context length & settings (running it as we speak)

~30GB in Q8 sure, but it's a minimal gain for double the VRAM usage.