mradermacher/Qwen2.5-32B-Instruct-GGUF

About

static quants of https://huggingface.co/Qwen/Qwen2.5-32B-Instruct

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-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	IQ3_XS	13.8
GGUF	IQ3_S	14.5	beats Q3_K*
GGUF	IQ3_M	14.9
GGUF	Q4_0	18.7	fast, low quality
GGUF	Q4_0_4_4	18.7	fast on arm, low quality
GGUF	Q4_0_4_8	18.7	fast on arm+i8mm, low quality
GGUF	Q4_0_8_8	18.7	fast on arm+sve, low quality
GGUF	IQ4_NL	18.9	prefer IQ4_XS
GGUF	Q4_1	20.7
GGUF	Q5_0	22.7
PART 1 PART 2	Q2_K	24.7
GGUF	Q5_1	24.7
PART 1 PART 2	Q3_K_S	28.9
PART 1 PART 2	Q3_K_M	32.0	lower quality
PART 1 PART 2	Q3_K_L	34.6
PART 1 PART 2	IQ4_XS	35.8
PART 1 PART 2	Q4_K_S	37.7	fast, recommended
PART 1 PART 2	Q4_K_M	39.8	fast, recommended
PART 1 PART 2	Q5_K_S	45.4
PART 1 PART 2	Q5_K_M	46.6
PART 1 PART 2	Q6_K	53.9	very good quality
PART 1 PART 2	SOURCE	65.6	source gguf, only provided when it was hard to come by
PART 1 PART 2	Q8_0	69.7	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.