Llm GGUF models
309 GGUF models in the Llm family, quantized by 125 uploaders. Sizes run from 2M to 73.2B parameters. The longest trained context is 256K tokens.
About the Llm GGUF models
Llm is represented on ggufmodels.com by 309 GGUF models, quantized by 125 uploaders on Hugging Face. The most downloaded are Llm Jp 4 33b Thinking, Llm Jp 4.1 32b A3B Thinking and Llm Jp 4.1 33b Thinking. Parameter counts run from 2M to 73.2B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Llm model is between 0.0 to 45.4 GB, which is the quant most people start with. Most files come from mradermacher (50), mmnga (20) and featherless-ai-quants (19). The quants you will meet most often are Q4_K_M (218), Q8_0 (185), Q5_K_M (146) and Q6_K (144), where the number is how many models offer that quant.
Frequently asked questions
Which Llm GGUF should I download?
The most downloaded Llm GGUF here is Llm Jp 4 33b Thinking. 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 Llm model need?
Q4_K_M files of Llm models on this site range from 0.0 to 45.4 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 Llm GGUF files come from?
The most common quantizers here are mradermacher, mmnga and featherless-ai-quants. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.