Lora GGUF models
153 GGUF models in the Lora family, quantized by 97 uploaders. Sizes run from 3M to 14.3B parameters. The longest trained context is 128K tokens.
About the Lora GGUF models
Lora is represented on ggufmodels.com by 153 GGUF models, quantized by 97 uploaders on Hugging Face. The most downloaded are lora2, lora unity xr v1 and lora model lamma3.1 7b. Parameter counts run from 3M to 14.3B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Lora model is between 0.1 to 7.5 GB, which is the quant most people start with. Most files come from ViktorMardskog (10), d8912046 (7) and Gonzalo33 (5). The quants you will meet most often are Q4_K_M (81), Q8_0 (48), F16 (31) and Q5_K_M (21), where the number is how many models offer that quant.
Frequently asked questions
Which Lora GGUF should I download?
The most downloaded Lora GGUF here is lora2. 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 Lora model need?
Q4_K_M files of Lora models on this site range from 0.1 to 7.5 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 Lora GGUF files come from?
The most common quantizers here are ViktorMardskog, d8912046 and Gonzalo33. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.