Airoboros GGUF models
221 GGUF models in the Airoboros family, quantized by 14 uploaders. Sizes run from 61M to 179B parameters. The longest trained context is 195K tokens.
About the Airoboros GGUF models
Airoboros is represented on ggufmodels.com by 221 GGUF models, quantized by 14 uploaders on Hugging Face. The most downloaded are Airoboros L2 70b 2.2, Airoboros L2 7B 2.1 and Airoboros L2 13B 2.1. Parameter counts run from 61M to 179B, and the longest trained context window is 195K tokens.
A Q4_K_M file of a Airoboros model is between 0.0 to 108.3 GB, which is the quant most people start with. Most files come from mradermacher (149), TheBloke (36) and tensorblock (10). The quants you will meet most often are Q2_K (211), Q4_K_M (203), Q5_K_M (200) and Q3_K_M (200), where the number is how many models offer that quant.
Frequently asked questions
Which Airoboros GGUF should I download?
The most downloaded Airoboros GGUF here is Airoboros L2 70b 2.2. 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 Airoboros model need?
Q4_K_M files of Airoboros models on this site range from 0.0 to 108.3 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 Airoboros GGUF files come from?
The most common quantizers here are mradermacher, TheBloke and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.