Laguna GGUF models
70 GGUF models in the Laguna family, quantized by 50 uploaders. Sizes run from 164M to 226B parameters. The longest trained context is 1024K tokens.
About the Laguna GGUF models
Laguna is represented on ggufmodels.com by 70 GGUF models, quantized by 50 uploaders on Hugging Face. The most downloaded are Laguna XS 2.1 APEX, Laguna S 2.1 and Laguna XS 2.1. Parameter counts run from 164M to 226B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Laguna model is between 0.3 to 136.1 GB, which is the quant most people start with. Most files come from mradermacher (6), poolside-laguna-hackathon (3) and Lucebox (3). The quants you will meet most often are Q4_K_M (35), Q8_0 (23), Q6_K (22) and Q5_K_M (16), where the number is how many models offer that quant.
Frequently asked questions
Which Laguna GGUF should I download?
The most downloaded Laguna GGUF here is Laguna XS 2.1 APEX. 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 Laguna model need?
Q4_K_M files of Laguna models on this site range from 0.3 to 136.1 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 Laguna GGUF files come from?
The most common quantizers here are mradermacher, poolside-laguna-hackathon and Lucebox. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.