Finetuned GGUF models
82 GGUF models in the Finetuned family, quantized by 41 uploaders. Sizes run from 3M to 20.9B parameters. The longest trained context is 128K tokens.
About the Finetuned GGUF models
Finetuned is represented on ggufmodels.com by 82 GGUF models, quantized by 41 uploaders on Hugging Face. The most downloaded are finetuned t5 cnn dailymail, clinicalnlplab/finetuned-PMCLLaMA-PubmedSumm and finetuned dialoGPT mental health llm v1. Parameter counts run from 3M to 20.9B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Finetuned model is between 0.0 to 7.9 GB, which is the quant most people start with. Most files come from mradermacher (22), RichardErkhov (8) and CPSC532 (6). The quants you will meet most often are Q4_K_M (56), Q5_K_M (41), Q2_K (35) and Q8_0 (34), where the number is how many models offer that quant.
Frequently asked questions
Which Finetuned GGUF should I download?
The most downloaded Finetuned GGUF here is finetuned t5 cnn dailymail. 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 Finetuned model need?
Q4_K_M files of Finetuned models on this site range from 0.0 to 7.9 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 Finetuned GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and CPSC532. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.