For a 16Gb card I use UD-IQ4_XS with 94208 of context and Q4 for KV cache. But I don't have desktop on this GPU, so you'll need to either reduce the context size or use a 3 bit quant.

It's is a dense model, so RAM is irrelevant. It will be too slow if the model leaks into RAM. You'll need to put all layers on the GPU.

But what is your GPU? It's a dense model, running it from RAM will be extremely slow.

If you want to utilize your RAM, you need a MoE model.

What are your specs?

Same thing, I bought mine last month!

I offload mmproj to the CPU to keep as much model weights in VRAM as possible 🙂

27B and Qwen flash next can run with somewhat realistic specs. I run 27B on my 7900 XTX.

It's not a BJD - it's a purple mermaid Barbie from Dreamtopia series. I re-bodied her to MengF Pink White body from Aliexpress to give her legs. Some people also use Barbie Tennis player as a "body donor" 😅 It's a cheap playline doll, but she is gorgeous, probably my favorite Barbie.

That would be such a good title! Why didn't I think of that? 😅

The woman’s modelling career.

WDYM? The joke about Chinese models (like Qwen, DeepSeek, etc.) won't work without this.

Yeah, 27B only usable if you can fit it entirely in VRAM. Only MoE models are fine to split, like the mentioned Qwen 3.8 Flash Next. Even though it's large, only the active 6B parameters needs to be located in VRAM, the rest can be in RAM and SSD.

Nice to hear!

Please, ping me once you get the approval, I prefer F-Droid over Obtainium 🙂