mradermacher/DeepSeek-R1-Distill-Llama-8B-Abliterated-i1-GGUF

---

base_model: stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated language:

• en

library_name: transformers quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated

static quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Abliterated-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
PART 1 PART 2	i1-IQ1_S	4.1	for the desperate
PART 1 PART 2	i1-IQ1_M	4.4	mostly desperate
PART 1 PART 2	i1-IQ2_XXS	4.9
PART 1 PART 2	i1-IQ2_XS	5.3
PART 1 PART 2	i1-IQ2_S	5.6
PART 1 PART 2	i1-IQ2_M	6.0
PART 1 PART 2	i1-Q2KS	6.1	very low quality
PART 1 PART 2	i1-Q2K	6.5	IQ3XXS probably better
PART 1 PART 2	i1-IQ3_XXS	6.6	lower quality
PART 1 PART 2	i1-IQ3_XS	7.1
PART 1 PART 2	i1-Q3KS	7.4	IQ3_XS probably better
PART 1 PART 2	i1-IQ3S	7.5	beats Q3K*
PART 1 PART 2	i1-IQ3_M	7.7
PART 1 PART 2	i1-Q3KM	8.1	IQ3_S probably better
PART 1 PART 2	i1-Q3KL	8.7	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	9.0
PART 1 PART 2	i1-Q4_0	9.5	fast, low quality
PART 1 PART 2	i1-IQ4NL	9.5	prefer IQ4XS
PART 1 PART 2	i1-Q4KS	9.5	optimal size/speed/quality
PART 1 PART 2	i1-Q4KM	9.9	fast, recommended
PART 1 PART 2	i1-Q4_1	10.4
PART 1 PART 2	i1-Q5KS	11.3
PART 1 PART 2	i1-Q5KM	11.6
PART 1 PART 2	i1-Q6K	13.3	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.