Quantization Request for https://huggingface.co/DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

#2917
by xsgaaa - opened

Hi mradermacher,

Would you mind quantizing this model when you have a chance?

https://huggingface.co/DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

Thank you very much!

Isn't this already a quantized version of this model?

it's a gguf, already quanted

Isn't this already a quantized version of this model?

The original model is a bit large for my setup. Would it be possible to provide smaller-sized versions at the same quantization levels?

it's a gguf, already quanted

The original model is a bit large for my setup. Would it be possible to provide smaller-sized versions at the same quantization levels?

Would it be possible to provide smaller-sized versions at the same quantization levels?

No. How would it be possible to do that? If you want to put 1 liter of water into less than 1 liter of bottle, it wouldnt be possible? Just get a bigger bottle (bigger gpu), get less water (smaller quant) or get more bottles (offload to cpu or multiple gpu), or simply switch the water (get different model)

Sign up or log in to comment