[SlavikCA]

I'm getting 30 t/s on RTX 4090D (using 42 out of 48GB VRAM) with UD-Q6_K_XL

https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/discussions/...

[maxloh]

I thought Q4_K_M is the standard. Why did you choose the 6-bit variant? Does it generate better input?

[SlavikCA]

There is no standard.

The higher quantization - the better results, but more memory is needed. Q8 is the best.

[SV_BubbleTime]

FP32 is best, although I wonder if there isn’t something better I don’t know about. Q8 is for the most part equal to FP16 in practical terms by being smart about what is quantized, but iirc always slower than FP16 and FP8.