mradermacher/MiniMax-M2-REAP-139B-A10B-i1-GGUF

---

base_model: cerebras/MiniMax-M2-REAP-139B-A10B language:

• en

library_name: transformers license: other mradermacher: readme_rev: 1 quantized_by: mradermacher tags:

• minimax
• MOE
• pruning
• compression

---

About

weighted/imatrix quants of https://huggingface.co/cerebras/MiniMax-M2-REAP-139B-A10B

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

static quants are available at https://huggingface.co/mradermacher/MiniMax-M2-REAP-139B-A10B-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	0.4	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	28.6	for the desperate
GGUF	i1-IQ1_M	31.7	mostly desperate
GGUF	i1-IQ2_XXS	36.8
GGUF	i1-IQ2_XS	41.0
GGUF	i1-IQ2_S	41.7
GGUF	i1-IQ2_M	45.8
GGUF	i1-Q2K_S	47.4	very low quality
PART 1 PART 2	i1-Q2K	50.9	IQ3XXS probably better
PART 1 PART 2	i1-IQ3_XXS	53.7	lower quality
PART 1 PART 2	i1-IQ3_XS	57.0
PART 1 PART 2	i1-Q3KS	60.2	IQ3_XS probably better
PART 1 PART 2	i1-IQ3S	60.3	beats Q3K*
PART 1 PART 2	i1-IQ3_M	61.1
PART 1 PART 2	i1-Q3KM	66.7	IQ3_S probably better
PART 1 PART 2	i1-Q3KL	72.2	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	74.3
PART 1 PART 2	i1-Q4_0	79.0	fast, low quality
PART 1 PART 2	i1-Q4KS	79.3	optimal size/speed/quality
PART 1 PART 2	i1-Q4KM	84.3	fast, recommended
PART 1 PART 2	i1-Q4_1	87.3
PART 1 PART 2	i1-Q5KS	96.0
PART 1 PART 2	i1-Q5KM	98.9
PART 1 PART 2 PART 3	i1-Q6K	114.4	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.