mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUF

---

base_model: AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts datasets:

• AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations

language:

• en

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

• mixture-of-experts
• moe
• expert-pruning
• gpt-oss
• openai
• reasoning
• all
• specialized
• efficient
• transformer
• causal-lm
• text-generation
• pytorch
• pruned-model
• domain-specific

---

About

weighted/imatrix quants of https://huggingface.co/AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts

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

static quants are available at https://huggingface.co/mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-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_M	3.7	mostly desperate
GGUF	i1-IQ1_S	3.7	for the desperate
GGUF	i1-IQ2_XXS	3.7
GGUF	i1-IQ2_XS	3.7
GGUF	i1-Q2K_S	3.7	very low quality
GGUF	i1-Q3KS	3.7	IQ3XS probably better
GGUF	i1-IQ2_M	3.7
GGUF	i1-IQ2_S	3.7
GGUF	i1-IQ3S	3.7	beats Q3K*
GGUF	i1-IQ3_XS	3.7
GGUF	i1-IQ3_XXS	3.7	lower quality
GGUF	i1-Q2K	3.7	IQ3XXS probably better
GGUF	i1-IQ4_XS	3.8
GGUF	i1-IQ4NL	3.8	prefer IQ4XS
GGUF	i1-Q4_0	3.8	fast, low quality
GGUF	i1-IQ3_M	3.8
GGUF	i1-Q3KM	4.0	IQ3S probably better
GGUF	i1-Q3KL	4.1	IQ3M probably better
GGUF	i1-Q4_1	4.1
GGUF	i1-Q4K_S	4.4	optimal size/speed/quality
GGUF	i1-Q4K_M	4.7	fast, recommended
GGUF	i1-Q5K_S	4.8
GGUF	i1-Q5K_M	5.0
GGUF	i1-Q6K	6.4	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.