mradermacher/Nemotron-4-340B-Instruct-hf-GGUF

About

static quants of https://huggingface.co./mgoin/Nemotron-4-340B-Instruct-hf

weighted/imatrix quants are available at https://huggingface.co./mradermacher/Nemotron-4-340B-Instruct-hf-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
PART 1 PART 2 PART 3	Q2_K	131.6
PART 1 PART 2 PART 3	IQ3_XS	142.6
PART 1 PART 2 PART 3 PART 4	Q3_K_S	148.5
PART 1 PART 2 PART 3 PART 4	IQ3_S	148.9	beats Q3_K*
PART 1 PART 2 PART 3 PART 4	IQ3_M	155.4
PART 1 PART 2 PART 3 PART 4	Q3_K_M	171.6	lower quality
PART 1 PART 2 PART 3 PART 4	IQ4_XS	185.6
PART 1 PART 2 PART 3 PART 4	Q3_K_L	191.3
PART 1 PART 2 PART 3 PART 4	Q4_K_S	195.2	fast, recommended
P1 P2 P3 P4 P5	Q4_K_M	210.3	fast, recommended
P1 P2 P3 P4 P5	Q5_K_S	235.2
P1 P2 P3 P4 P5	Q5_K_M	244.1
P1 P2 P3 P4 P5 P6	Q6_K	279.9	very good quality
P1 P2 P3 P4 P5 P6 P7 P8	Q8_0	362.5	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.