mradermacher/DeepSeek-Coder-V2-Lite-Base-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co./deepseek-ai/DeepSeek-Coder-V2-Lite-Base

static quants are available at https://huggingface.co./mradermacher/DeepSeek-Coder-V2-Lite-Base-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	i1-IQ1_S	5.1	for the desperate
GGUF	i1-IQ1_M	5.3	mostly desperate
GGUF	i1-IQ2_XXS	5.7
GGUF	i1-IQ2_XS	6.1
GGUF	i1-IQ2_S	6.1
GGUF	i1-IQ2_M	6.4
GGUF	i1-Q2_K	6.5	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	7.1	lower quality
GGUF	i1-IQ3_XS	7.2
GGUF	i1-IQ3_S	7.6	beats Q3_K*
GGUF	i1-Q3_K_S	7.6	IQ3_XS probably better
GGUF	i1-IQ3_M	7.7
GGUF	i1-Q3_K_M	8.2	IQ3_S probably better
GGUF	i1-Q3_K_L	8.6	IQ3_M probably better
GGUF	i1-IQ4_XS	8.7
GGUF	i1-Q4_0	9.0	fast, low quality
GGUF	i1-Q4_K_S	9.6	optimal size/speed/quality
GGUF	i1-Q4_K_M	10.5	fast, recommended
GGUF	i1-Q5_K_S	11.2
GGUF	i1-Q5_K_M	12.0
GGUF	i1-Q6_K	14.2	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.