Aura GGUF models
83 GGUF models in the Aura family, quantized by 25 uploaders. Sizes run from 109M to 30.7B parameters. The longest trained context is 1000K tokens.
About the Aura GGUF models
Aura is represented on ggufmodels.com by 83 GGUF models, quantized by 25 uploaders on Hugging Face. The most downloaded are Aura Prototype 26B A4B, Aura 4B and Aura-Uncensored-OAS-8B-L3. Parameter counts run from 109M to 30.7B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Aura model is between 0.1 to 17.2 GB, which is the quant most people start with. Most files come from mradermacher (41), jeiku (7) and itlwas (4). The quants you will meet most often are Q4_K_M (66), Q6_K (53), Q5_K_M (49) and Q2_K (49), where the number is how many models offer that quant.
Frequently asked questions
Which Aura GGUF should I download?
The most downloaded Aura GGUF here is Aura Prototype 26B A4B. 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 Aura model need?
Q4_K_M files of Aura models on this site range from 0.1 to 17.2 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 Aura GGUF files come from?
The most common quantizers here are mradermacher, jeiku and itlwas. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.