mradermacher/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B-i1-GGUF

---

basemodel: cloudyu/TruthfulDPOcloudyuMixtral34Bx2MoE_60B language:

• en

library_name: transformers license: mit quantized_by: mradermacher tags:

• moe
• DPO
• RL-TUNED

---

About

weighted/imatrix quants of https://huggingface.co/cloudyu/TruthfulDPOcloudyuMixtral34Bx2MoE60B

static quants are available at https://huggingface.co/mradermacher/TruthfulDPOcloudyuMixtral34Bx2MoE60B-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	i1-IQ1_S	12.9	for the desperate
GGUF	i1-IQ1_M	14.2	mostly desperate
GGUF	i1-IQ2_XXS	16.3
GGUF	i1-IQ2_XS	18.1
GGUF	i1-IQ2_S	18.8
GGUF	i1-IQ2_M	20.5
GGUF	i1-Q2K	22.5	IQ3XXS probably better
GGUF	i1-IQ3_XXS	23.6	lower quality
GGUF	i1-IQ3_XS	25.1
GGUF	i1-Q3KS	26.4	IQ3XS probably better
GGUF	i1-IQ3S	26.5	beats Q3K*
GGUF	i1-IQ3_M	27.2
GGUF	i1-Q3KM	29.3	IQ3S probably better
GGUF	i1-Q3KL	31.9	IQ3M probably better
GGUF	i1-IQ4_XS	32.6
GGUF	i1-Q4_0	34.6	fast, low quality
GGUF	i1-Q4K_S	34.7	optimal size/speed/quality
GGUF	i1-Q4K_M	36.8	fast, recommended
GGUF	i1-Q5K_S	42.0
GGUF	i1-Q5K_M	43.2
GGUF	i1-Q6K	50.0	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.