Medgemma GGUF models
194 GGUF models in the Medgemma family, quantized by 112 uploaders. Sizes run from 12M to 28.4B parameters. The longest trained context is 128K tokens.
About the Medgemma GGUF models
Medgemma is represented on ggufmodels.com by 194 GGUF models, quantized by 112 uploaders on Hugging Face. The most downloaded are Medgemma-4B-It, Medgemma-1.5-4B-It and Medgemma-27B-Text-It. Parameter counts run from 12M to 28.4B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Medgemma model is between 2.5 to 17.3 GB, which is the quant most people start with. Most files come from mradermacher (36), unsloth (4) and bolmu321 (4). The quants you will meet most often are Q4_K_M (119), Q5_K_M (72), Q8_0 (68) and Q6_K (66), where the number is how many models offer that quant.
Frequently asked questions
Which Medgemma GGUF should I download?
The most downloaded Medgemma GGUF here is Medgemma-4B-It. 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 Medgemma model need?
Q4_K_M files of Medgemma models on this site range from 2.5 to 17.3 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 Medgemma GGUF files come from?
The most common quantizers here are mradermacher, unsloth and bolmu321. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.