mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-i1-GGUF

---

base_model: urufura/NVIDIA-Nemotron-Nano-9B-v2-Japanese datasets:

• nvidia/Nemotron-Personas-Japan
• nvidia/Nemotron-CC-v2.1
• nvidia/Nemotron-Pretraining-Specialized-v1
• nvidia/Nemotron-Agentic-v1
• nvidia/Nemotron-Instruction-Following-Chat-v1
• globis-university/aozorabunko-clean
• HuggingFaceFW/fineweb-2

language:

• en
• ja

library_name: transformers license: other license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/ license_name: nvidia-nemotron-open-model-license mradermacher: readme_rev: 1 quantized_by: mradermacher tags:

• nvidia
• pytorch

---

About

weighted/imatrix quants of https://huggingface.co/urufura/NVIDIA-Nemotron-Nano-9B-v2-Japanese

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

static quants are available at https://huggingface.co/mradermacher/NVIDIA-Nemotron-Nano-9B-v2-Japanese-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_S	4.9	for the desperate
GGUF	i1-IQ1_M	5.0	mostly desperate
GGUF	i1-IQ2_XXS	5.0
GGUF	i1-IQ2_XS	5.0
GGUF	i1-IQ2_S	5.1
GGUF	i1-IQ2_M	5.1
GGUF	i1-Q2K	5.1	IQ3XXS probably better
GGUF	i1-Q2K_S	5.2	very low quality
GGUF	i1-IQ3_XXS	5.2	lower quality
GGUF	i1-IQ3S	5.2	beats Q3K*
GGUF	i1-IQ3_XS	5.2
GGUF	i1-Q3KS	5.2	IQ3XS probably better
GGUF	i1-IQ3_M	5.3
GGUF	i1-IQ4_XS	5.4
GGUF	i1-IQ4NL	5.4	prefer IQ4XS
GGUF	i1-Q4_0	5.4	fast, low quality
GGUF	i1-Q3KM	5.5	IQ3S probably better
GGUF	i1-Q3KL	5.6	IQ3M probably better
GGUF	i1-Q4_1	5.9
GGUF	i1-Q4K_S	6.3	optimal size/speed/quality
GGUF	i1-Q4K_M	6.6	fast, recommended
GGUF	i1-Q5K_S	6.9
GGUF	i1-Q5K_M	7.2
GGUF	i1-Q6K	9.2	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.