Medical GGUF models
264 GGUF models in the Medical family, quantized by 139 uploaders. Sizes run from 23M to 32.8B parameters. The longest trained context is 256K tokens.
About the Medical GGUF models
Medical is represented on ggufmodels.com by 264 GGUF models, quantized by 139 uploaders on Hugging Face. The most downloaded are II Medical 8B, II Medical 8B 1706 GGUF and II Medical 8B 1706. Parameter counts run from 23M to 32.8B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Medical model is between 0.0 to 19.8 GB, which is the quant most people start with. Most files come from mradermacher (81), piyushf (21) and yc1154645 (4). The quants you will meet most often are Q8_0 (180), Q4_K_M (116), Q5_K_M (99) and Q3_K_M (97), where the number is how many models offer that quant.
Frequently asked questions
Which Medical GGUF should I download?
The most downloaded Medical GGUF here is II Medical 8B. 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 Medical model need?
Q4_K_M files of Medical models on this site range from 0.0 to 19.8 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 Medical GGUF files come from?
The most common quantizers here are mradermacher, piyushf and yc1154645. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.