Appvoid GGUF models
79 GGUF models in the Appvoid family, quantized by 2 uploaders. Sizes run from 118M to 2.41B parameters. The longest trained context is 125K tokens.
About the Appvoid GGUF models
Appvoid is represented on ggufmodels.com by 79 GGUF models, quantized by 2 uploaders on Hugging Face. The most downloaded are appvoid arco exp 29, Appvoid Void.0 Cpt and appvoid arco exp 11. Parameter counts run from 118M to 2.41B, and the longest trained context window is 125K tokens.
A Q4_K_M file of a Appvoid model is between 0.3 to 1.5 GB, which is the quant most people start with. Most files come from RichardErkhov (76) and appvoid (3). The quants you will meet most often are Q8_0 (77), Q6_K (76), Q5_K_S (76) and Q5_K_M (76), where the number is how many models offer that quant.
Frequently asked questions
Which Appvoid GGUF should I download?
The most downloaded Appvoid GGUF here is appvoid arco exp 29. 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 Appvoid model need?
Q4_K_M files of Appvoid models on this site range from 0.3 to 1.5 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 Appvoid GGUF files come from?
The most common quantizers here are RichardErkhov and appvoid. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.