Pllum GGUF models
80 GGUF models in the Pllum family, quantized by 16 uploaders. Sizes run from 3.88B to 46.7B parameters. The longest trained context is 1000K tokens.
About the Pllum GGUF models
Pllum is represented on ggufmodels.com by 80 GGUF models, quantized by 16 uploaders on Hugging Face. The most downloaded are PLLuM 12B Base 250801, PLLuM 8x7B Chat 2412 and PLLuM 12B Instruct 2512. Parameter counts run from 3.88B to 46.7B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Pllum model is between 2.5 to 28.4 GB, which is the quant most people start with. Most files come from mradermacher (49), Jerzman (6) and najdek (4). The quants you will meet most often are Q4_K_M (61), Q6_K (58), Q5_K_M (54) and Q2_K (54), where the number is how many models offer that quant.
Frequently asked questions
Which Pllum GGUF should I download?
The most downloaded Pllum GGUF here is PLLuM 12B Base 250801. 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 Pllum model need?
Q4_K_M files of Pllum models on this site range from 2.5 to 28.4 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 Pllum GGUF files come from?
The most common quantizers here are mradermacher, Jerzman and najdek. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.