from nobodywho import Chat

chat = Chat("huggingface:NobodyWho/Google_Gemma3-12B-GGUF/gemma-3-12b-it-Q4_K_M.gguf")
response = chat.ask("What is the capital of Denmark?").completed()
print(response) # Copenhagen!

Vision

python

from nobodywho import Model, Chat, Prompt, Image, Text

model = Model(
    "huggingface:NobodyWho/Google_Gemma3-12B-GGUF/gemma-3-12b-it-Q4_K_M.gguf",
    projection_model_path="huggingface:NobodyWho/Google_Gemma3-12B-GGUF/mmproj-BF16.gguf"
)
chat = Chat(model, system_prompt="You are a helpful assistant.")

prompt = Prompt([
    Text("What do you see in this image?"),
    Image("./photo.png"),
])
response = chat.ask(prompt).completed()
print(response)

Prefer a manual download (e.g. for the Godot or Flutter binding)? Grab the files through the huggingface UI, or:

bash

wget https://huggingface.co/NobodyWho/Google_Gemma3-12B-GGUF/resolve/main/gemma-3-12b-it-Q4_K_M.gguf
wget https://huggingface.co/NobodyWho/Google_Gemma3-12B-GGUF/resolve/main/mmproj-BF16.gguf

and pass the local paths instead.

Benchmarks

Coming soon.

How are these GGUFs different?

These GGUF files serve mainly for NobodyWho inference library and are a way that we can guarantee that they will include all of the necessary info to be truly portable (sampler config, token descriptions, etc.). It is our informal effort to somehow arrive at more standardized GGUF files, which contain everything the runtime needs so that the user can have effortless experience using them, without additional fiddling or patching stuff up for every single model.

Model Details

Property	Value
Parameters	12B
Context length	131,072 tokens
Knowledge cutoff	August 2024
Languages	140+
License	Gemma Terms of Use
Base model	google/gemma-3-12b-it

Credits

GGUF quantizations provided by unsloth. Thanks!