mradermacher/Mistral-2x24B-MOE-Power-Magistral-Devstral-Reasoning-Ultimate-44B-i1-GGUF

---

base_model: DavidAU/Mistral-2x24B-MOE-Power-Magistral-Devstral-Reasoning-Ultimate-44B language:

• en
• fr
• de
• es
• pt
• it
• ja
• ko
• ru
• zh
• ar
• fa
• id
• ms
• ne
• pl
• ro
• sr
• sv
• tr
• uk
• vi
• hi
• bn

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

• merge
• programming
• code generation
• Codestral
• code
• moe
• coding
• coder
• chat
• mistral
• mixtral
• mixture of experts
• mistral moe
• 2X24B
• reasoning
• thinking
• Devstral
• Magistral

---

About

weighted/imatrix quants of https://huggingface.co/DavidAU/Mistral-2x24B-MOE-Power-Magistral-Devstral-Reasoning-Ultimate-44B

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

static quants are available at https://huggingface.co/mradermacher/Mistral-2x24B-MOE-Power-Magistral-Devstral-Reasoning-Ultimate-44B-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 qwuants)
GGUF	i1-IQ1_S	9.4	for the desperate
GGUF	i1-IQ1_M	10.3	mostly desperate
GGUF	i1-IQ2_XXS	11.9
GGUF	i1-IQ2_XS	13.2
GGUF	i1-IQ2_S	13.5
GGUF	i1-IQ2_M	14.8
GGUF	i1-Q2K_S	15.2	very low quality
GGUF	i1-Q2K	16.3	IQ3XXS probably better
GGUF	i1-IQ3_XXS	17.1	lower quality
GGUF	i1-IQ3_XS	18.2
GGUF	i1-Q3KS	19.2	IQ3XS probably better
GGUF	i1-IQ3S	19.2	beats Q3K*
GGUF	i1-IQ3_M	19.5
GGUF	i1-Q3KM	21.2	IQ3S probably better
GGUF	i1-Q3KL	22.9	IQ3M probably better
GGUF	i1-IQ4_XS	23.6
GGUF	i1-Q4_0	25.0	fast, low quality
GGUF	i1-Q4K_S	25.1	optimal size/speed/quality
GGUF	i1-Q4K_M	26.6	fast, recommended
GGUF	i1-Q4_1	27.6
GGUF	i1-Q5K_S	30.2
GGUF	i1-Q5K_M	31.2
GGUF	i1-Q6K	36.0	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.