Cydonia GGUF models
203 GGUF models in the Cydonia family, quantized by 23 uploaders. Sizes run from 6.64B to 23.6B parameters. The longest trained context is 128K tokens.
About the Cydonia GGUF models
Cydonia is represented on ggufmodels.com by 203 GGUF models, quantized by 23 uploaders on Hugging Face. The most downloaded are Cydonia 24B v4.3, Cydonia 24B v4.2.0 and Cydonia 24B v4.3 Absolute Heresy. Parameter counts run from 6.64B to 23.6B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Cydonia model is between 4.0 to 14.3 GB, which is the quant most people start with. Most files come from BeaverAI (74), mradermacher (66) and bartowski (16). The quants you will meet most often are Q4_K_M (188), Q6_K (183), Q3_K_M (183) and Q5_K_M (182), where the number is how many models offer that quant.
Frequently asked questions
Which Cydonia GGUF should I download?
The most downloaded Cydonia GGUF here is Cydonia 24B v4.3. 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 Cydonia model need?
Q4_K_M files of Cydonia models on this site range from 4.0 to 14.3 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 Cydonia GGUF files come from?
The most common quantizers here are BeaverAI, mradermacher and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.