You can deploy this model and start earning money today!

mradermacher/
Qwen3-Next-80B-A3B-Instruct-Decensored-i1-GGUF

Name: Qwen3-Next-80B-A3B-Instruct-Decensored-i1-GGUF
Availability: InStock

transformers

gguf

generated_from_trainer

dpo

trl

Shifusen/Qwen3-Next-80B-A3B-Instruct-Decensored

Views

No views yet

About

weighted/imatrix quants of https://huggingface.co/Shifusen/Qwen3-Next-80B-A3B-Instruct-Decensored

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

static quants are available at https://huggingface.co/mradermacher/Qwen3-Next-80B-A3B-Instruct-Decensored-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	0.6	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	16.3	for the desperate
GGUF	i1-IQ1_M	18.1	mostly desperate
GGUF	i1-IQ2_XXS	21.1
GGUF	i1-IQ2_XS	23.5
GGUF	i1-IQ2_S	23.7
GGUF	i1-IQ2_M	26.2
GGUF	i1-Q2_K_S	27.4	very low quality
GGUF	i1-Q2_K	29.2	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	30.9	lower quality
GGUF	i1-IQ3_XS	32.8
GGUF	i1-Q3_K_S	34.6	IQ3_XS probably better
GGUF	i1-IQ3_S	34.6	beats Q3_K*
GGUF	i1-IQ3_M	35.1
GGUF	i1-Q3_K_M	38.3	IQ3_S probably better
GGUF	i1-Q3_K_L	41.3	IQ3_M probably better
GGUF	i1-IQ4_XS	42.7
GGUF	i1-Q4_0	45.4	fast, low quality
GGUF	i1-Q4_K_S	45.6	optimal size/speed/quality
GGUF	i1-Q4_K_M	48.5	fast, recommended
GGUF	i1-Q4_1	50.1
GGUF	i1-Q5_K_S	55.1
GGUF	i1-Q5_K_M	56.8
GGUF	i1-Q6_K	65.6	practically like static Q6_K

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.

mradermacher/Qwen3-Next-80B-A3B-Instruct-Decensored-i1-GGUF