Llama-4-Scout-17B-6E-Instruct-i1-GGUF/README.md

base_model, language, library_name, mradermacher, quantized_by, tags

base_model	language	library_name	mradermacher	quantized_by	tags
shadowlilac/Llama-4-Scout-17B-6E-Instruct	ar de en es fr hi id it pt th tl vi	transformers	readme_rev 1	mradermacher	pytorch llama llama-4 mixture of experts

About

weighted/imatrix quants of https://huggingface.co/shadowlilac/Llama-4-Scout-17B-6E-Instruct

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Llama-4-Scout-17B-6E-Instruct-GGUF

This is a vision model - mmproj files (if any) will be under files

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	i1-IQ2_XS	14.4
GGUF	i1-IQ3_XS	19.9
GGUF	i1-IQ4_XS	25.6
GGUF	i1-Q4_K_M	28.9	fast, recommended
GGUF	i1-Q5_K_M	33.8
GGUF	i1-Q6_K	39.0	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.