mradermacher/GPT-OSS-Swallow-20B-SFT-v0.1-i1-GGUF

---

base_model: tokyotech-llm/GPT-OSS-Swallow-20B-SFT-v0.1 datasets:

• tokyotech-llm/swallow-math-v2
• tokyotech-llm/swallow-code-v2
• tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1
• tokyotech-llm/lmsys-chat-1m-synth

language:

• en
• ja

library_name: transformers license: apache-2.0 model_type: ~ mradermacher: readme_rev: 1 quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/tokyotech-llm/GPT-OSS-Swallow-20B-SFT-v0.1

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-Swallow-20B-SFT-v0.1-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	12.1	mostly desperate
GGUF	i1-IQ2_M	12.2
GGUF	i1-IQ3_XXS	12.2	lower quality
GGUF	i1-Q2K	12.2	IQ3XXS probably better
GGUF	i1-IQ4_XS	12.2
GGUF	i1-Q2K_S	12.2	very low quality
GGUF	i1-IQ3_M	12.3
GGUF	i1-Q3KM	13.0	IQ3S probably better
GGUF	i1-Q4K_S	14.8	optimal size/speed/quality
GGUF	i1-Q4K_M	15.9	fast, recommended
GGUF	i1-Q6K	22.3	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.