unsloth
/

DeepSeek-V3-0324-GGUF

Text Generation

Model card Files Files and versions

Resources

View closed (2)

IQ2_XXS optimal for me

#17 opened 7 months ago by

World's Largest Dataset

#16 opened 7 months ago by deleted

Re-converting the GGUF for MLA?

#15 opened 7 months ago by

What tool/framework to test gguf models?

#14 opened 7 months ago by

Request: DOI

#13 opened 8 months ago by

How to run ollama using these new quantized weights?

#12 opened 8 months ago by

Running Model "unsloth/DeepSeek-V3-0324-GGUF" with vLLM does not working

#11 opened 8 months ago by

The UD-IQ2_XXS is surprisingly good, but it's good to know that it degrades gradually but significantly after about 1000 tokens.

#9 opened 8 months ago by

671B params or 685B params?

#8 opened 8 months ago by

how to run tools use correctly

#7 opened 8 months ago by

How many bits of Quantization is enough for Code Generation Tasks?

#5 opened 8 months ago by

Added IQ1_S version to Ollama

#4 opened 8 months ago by

Is the 2.51bit model using imatrix?

#3 opened 8 months ago by

Will you release the imatrix.dat used for the quants?

#2 opened 8 months ago by

Would There be Dynamic Qunatized Versions like 2.51bit

#1 opened 8 months ago by