[mystraline]

Yep, thats it what it does. Only works with nvidia.

The difference it does use safetensors, and not gguf's. But it does dynamically requant to int4 8 or bf16.

[hasteg]

Wow that's actually sick as hell, somehow hadn't heard of this. maybe I will go and blow $700 on a new ram kit... thanks for sharing!

[mystraline]

Glad to share!

But go try it out now with a 35B model on your current hardware.

Right now, I have loaded qwen3.6-35B-A3B, 128k context, kv cache 2.5GB, thinking. Int8

Using 11.5GB gfx ram, 42GB system ram.

I dont want to oversell. All GPU would be faster, but creating a semi-unified system is deffo a game changer for me.