Helpingai GGUF models
79 GGUF models in the Helpingai family, quantized by 14 uploaders. Sizes run from 110M to 17.5B parameters. The longest trained context is 1024K tokens.
About the Helpingai GGUF models
Helpingai is represented on ggufmodels.com by 79 GGUF models, quantized by 14 uploaders on Hugging Face. The most downloaded are HelpingAI-15B, HelpingAI-9B and HelpingAI 3B hindi i1. Parameter counts run from 110M to 17.5B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Helpingai model is between 0.1 to 10.6 GB, which is the quant most people start with. Most files come from mradermacher (36), QuantFactory (10) and HelpingAI (8). The quants you will meet most often are Q4_K_M (71), Q2_K (58), Q3_K_M (57) and Q5_K_M (56), where the number is how many models offer that quant.
Frequently asked questions
Which Helpingai GGUF should I download?
The most downloaded Helpingai GGUF here is HelpingAI-15B. 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 Helpingai model need?
Q4_K_M files of Helpingai models on this site range from 0.1 to 10.6 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 Helpingai GGUF files come from?
The most common quantizers here are mradermacher, QuantFactory and HelpingAI. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.