Danube GGUF models
133 GGUF models in the Danube family, quantized by 35 uploaders. Sizes run from 514M to 3.96B parameters. The longest trained context is 16K tokens.
About the Danube GGUF models
Danube is represented on ggufmodels.com by 133 GGUF models, quantized by 35 uploaders on Hugging Face. The most downloaded are danube3-4B, danube2-1.8b-CodeFeedback and danube2-1.8b-Synthia-v1.3. Parameter counts run from 514M to 3.96B, and the longest trained context window is 16K tokens.
A Q4_K_M file of a Danube model is between 0.3 to 4.8 GB, which is the quant most people start with. Most files come from mradermacher (43), Felladrin (9) and adamo1139 (8). The quants you will meet most often are Q4_K_M (95), Q6_K (88), Q5_K_M (84) and Q2_K (82), where the number is how many models offer that quant.
Frequently asked questions
Which Danube GGUF should I download?
The most downloaded Danube GGUF here is danube3-4B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Danube model need?
Q4_K_M files of Danube models on this site range from 0.3 to 4.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Danube GGUF files come from?
The most common quantizers here are mradermacher, Felladrin and adamo1139. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.