mradermacher/Llama-3.1-Nemotron-93B-Instruct-HF-early-GGUF

About

static quants of https://huggingface.co./ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early

weighted/imatrix quants are available at https://huggingface.co./mradermacher/Llama-3.1-Nemotron-93B-Instruct-HF-early-i1-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	Q2_K	34.2
GGUF	Q3_K_S	40.0
GGUF	Q3_K_M	44.5	lower quality
GGUF	Q3_K_L	48.4
GGUF	IQ4_XS	49.9
PART 1 PART 2	Q4_K_S	52.5	fast, recommended
PART 1 PART 2	Q4_K_M	55.4	fast, recommended
PART 1 PART 2	Q5_K_S	63.5
PART 1 PART 2	Q5_K_M	65.2
PART 1 PART 2	Q6_K	75.5	very good quality
PART 1 PART 2	Q8_0	97.8	fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

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.