worldclasspun

joined 1 year ago
[โ€“] worldclasspun@programming.dev 1 points 2 weeks ago (1 children)

What are you using to run the model? Llama.cpp will automatically split the model between your system ram and graphics card's vram.

Qwen 3.6 is a mixture of experts model with only 3B parameters active at a time. Even without quantization your card could easily run that.

[โ€“] worldclasspun@programming.dev 4 points 1 month ago (4 children)

Is that quantized? 4 bit Qwen 3.6 can get 22tps on a 1060.