πŸ“‹ Model Description


base_model: deepseek-ai/deepseek-coder-1.3b-instruct language:
  • en
library_name: transformers license: other license_link: LICENSE license_name: deepseek quantized_by: mradermacher

About






weighted/imatrix quants of https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct


static quants are available at https://huggingface.co/mradermacher/deepseek-coder-1.3b-instruct-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)

LinkTypeSize/GBNotes
GGUFi1-IQ1_S0.5for the desperate
GGUFi1-IQ1_M0.5mostly desperate
GGUFi1-IQ2_XXS0.6
GGUFi1-IQ2_XS0.6
GGUFi1-IQ2_S0.6
GGUFi1-IQ2_M0.7
GGUFi1-Q2K0.7IQ3XXS probably better
GGUFi1-IQ3_XXS0.7lower quality
GGUFi1-IQ3_XS0.7
GGUFi1-IQ3S0.7beats Q3K*
GGUFi1-Q3KS0.7IQ3XS probably better
GGUFi1-IQ3_M0.8
GGUFi1-Q3KM0.8IQ3S probably better
GGUFi1-IQ4_XS0.8
GGUFi1-Q3KL0.8IQ3M probably better
GGUFi1-Q4_00.9fast, low quality
GGUFi1-Q4K_S0.9optimal size/speed/quality
GGUFi1-Q4K_M1.0fast, recommended
GGUFi1-Q5K_S1.1
GGUFi1-Q5K_M1.1
GGUFi1-Q6K1.3practically like static Q6K
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

!image.png

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.

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
deepseek-coder-1.3b-instruct.i1-IQ1_M.gguf
LFS
421.73 MB Download
deepseek-coder-1.3b-instruct.i1-IQ1_S.gguf
LFS
405.14 MB Download
deepseek-coder-1.3b-instruct.i1-IQ2_M.gguf
LFS Q2
526.29 MB Download
deepseek-coder-1.3b-instruct.i1-IQ2_S.gguf
LFS Q2
504.16 MB Download
deepseek-coder-1.3b-instruct.i1-IQ2_XS.gguf
LFS Q2
474.52 MB Download
deepseek-coder-1.3b-instruct.i1-IQ2_XXS.gguf
LFS Q2
449.39 MB Download
deepseek-coder-1.3b-instruct.i1-IQ3_M.gguf
LFS Q3
641.62 MB Download
deepseek-coder-1.3b-instruct.i1-IQ3_S.gguf
LFS Q3
612.09 MB Download
deepseek-coder-1.3b-instruct.i1-IQ3_XS.gguf
LFS Q3
584.95 MB Download
deepseek-coder-1.3b-instruct.i1-IQ3_XXS.gguf
LFS Q3
554.04 MB Download
deepseek-coder-1.3b-instruct.i1-IQ4_XS.gguf
LFS Q4
709.9 MB Download
deepseek-coder-1.3b-instruct.i1-Q2_K.gguf
LFS Q2
533.79 MB Download
deepseek-coder-1.3b-instruct.i1-Q3_K_L.gguf
LFS Q3
709.97 MB Download
deepseek-coder-1.3b-instruct.i1-Q3_K_M.gguf
LFS Q3
671.52 MB Download
deepseek-coder-1.3b-instruct.i1-Q3_K_S.gguf
LFS Q3
612.09 MB Download
deepseek-coder-1.3b-instruct.i1-Q4_0.gguf
Recommended LFS Q4
742.01 MB Download
deepseek-coder-1.3b-instruct.i1-Q4_K_M.gguf
LFS Q4
832.99 MB Download
deepseek-coder-1.3b-instruct.i1-Q4_K_S.gguf
LFS Q4
776.26 MB Download
deepseek-coder-1.3b-instruct.i1-Q5_K_M.gguf
LFS Q5
955.43 MB Download
deepseek-coder-1.3b-instruct.i1-Q5_K_S.gguf
LFS Q5
908.74 MB Download
deepseek-coder-1.3b-instruct.i1-Q6_K.gguf
LFS Q6
1.09 GB Download