Functiongemma GGUF models
125 GGUF models in the Functiongemma family, quantized by 91 uploaders. Sizes run from 4M to 596M parameters. The longest trained context is 40K tokens.
About the Functiongemma GGUF models
Functiongemma is represented on ggufmodels.com by 125 GGUF models, quantized by 91 uploaders on Hugging Face. The most downloaded are Functiongemma-270M-It, Home FunctionGemma 270m and Functiongemma 270m It. Parameter counts run from 4M to 596M, and the longest trained context window is 40K tokens.
A Q4_K_M file of a Functiongemma model is between 0.3 to 0.3 GB, which is the quant most people start with. Most files come from mingxilei (6), mradermacher (4) and bb-1122 (4). The quants you will meet most often are Q8_0 (71), Q4_K_M (44), F16 (38) and Q5_K_M (14), where the number is how many models offer that quant.
Frequently asked questions
Which Functiongemma GGUF should I download?
The most downloaded Functiongemma GGUF here is Functiongemma-270M-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 Functiongemma model need?
Q4_K_M files of Functiongemma models on this site range from 0.3 to 0.3 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 Functiongemma GGUF files come from?
The most common quantizers here are mingxilei, mradermacher and bb-1122. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.