mradermacher/ALIA-40b-instruct-2601-i1-GGUF

---

base_model: BSC-LT/ALIA-40b-instruct-2601 datasets:

• CohereLabs/ayadataset
• projecte-aina/CoQCat
• databricks/databricks-dolly-15k
• projecte-aina/dolly3kca
• projecte-aina/MentorES
• projecte-aina/MentorCA
• HuggingFaceH4/norobots
• projecte-aina/RAGMultilingual
• Unbabel/TowerBlocks-v0.2
• OpenAssistant/oasst2
• open-r1/OpenR1-Math-220k
• HuggingFaceFW/fineweb-edu
• allenai/WildChat-1M

language:

• ca
• en
• es
• eu
• gl

library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/BSC-LT/ALIA-40b-instruct-2601

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

static quants are available at https://huggingface.co/mradermacher/ALIA-40b-instruct-2601-GGUF

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	imatrix	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	9.8	for the desperate
GGUF	i1-IQ1_M	10.6	mostly desperate
GGUF	i1-IQ2_XXS	11.8
GGUF	i1-IQ2_XS	12.9
GGUF	i1-IQ2_S	13.7
GGUF	i1-IQ2_M	14.6
GGUF	i1-Q2K_S	14.8	very low quality
GGUF	i1-Q2K	15.8	IQ3XXS probably better
GGUF	i1-IQ3_XXS	16.3	lower quality
GGUF	i1-IQ3_XS	17.5
GGUF	i1-Q3KS	18.3	IQ3XS probably better
GGUF	i1-IQ3S	18.4	beats Q3K*
GGUF	i1-IQ3_M	18.9
GGUF	i1-Q3KM	20.1	IQ3S probably better
GGUF	i1-Q3KL	21.7	IQ3M probably better
GGUF	i1-IQ4_XS	22.3
GGUF	i1-Q4_0	23.5	fast, low quality
GGUF	i1-Q4K_S	23.5	optimal size/speed/quality
GGUF	i1-Q4K_M	24.7	fast, recommended
GGUF	i1-Q4_1	25.8
GGUF	i1-Q5K_S	28.2
GGUF	i1-Q5K_M	28.9
GGUF	i1-Q6K	33.3	practically like static Q6K

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

!image.png

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.