Flan GGUF models
82 GGUF models in the Flan family, quantized by 40 uploaders. Sizes run from 77M to 19.5B parameters. The longest trained context is 512 tokens.
About the Flan GGUF models
Flan is represented on ggufmodels.com by 82 GGUF models, quantized by 40 uploaders on Hugging Face. The most downloaded are Flan T5 Xxl, Flan T5 Large Grammar Synthesis and flan-t5-xxl. Parameter counts run from 77M to 19.5B, and the longest trained context window is 512 tokens.
A Q4_K_M file of a Flan model is between 0.0 to 6.8 GB, which is the quant most people start with. Most files come from mradermacher (16), Felladrin (8) and pszemraj (4). The quants you will meet most often are Q4_K_M (46), Q8_0 (42), Q6_K (33) and Q5_K_M (25), where the number is how many models offer that quant.
Frequently asked questions
Which Flan GGUF should I download?
The most downloaded Flan GGUF here is Flan T5 Xxl. 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 Flan model need?
Q4_K_M files of Flan models on this site range from 0.0 to 6.8 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 Flan GGUF files come from?
The most common quantizers here are mradermacher, Felladrin and pszemraj. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.