Instructions to use unsloth/gemma-3-12b-it-qat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-3-12b-it-qat-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="unsloth/gemma-3-12b-it-qat-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("unsloth/gemma-3-12b-it-qat-GGUF")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/gemma-3-12b-it-qat-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/gemma-3-12b-it-qat-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/gemma-3-12b-it-qat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-3-12b-it-qat-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-3-12b-it-qat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/gemma-3-12b-it-qat-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/gemma-3-12b-it-qat-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-3-12b-it-qat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/gemma-3-12b-it-qat-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-3-12b-it-qat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use unsloth/gemma-3-12b-it-qat-GGUF with Ollama:
```
ollama run hf.co/unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use unsloth/gemma-3-12b-it-qat-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/gemma-3-12b-it-qat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gemma-3-12b-it-qat-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gemma-3-12b-it-qat-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Atomic Chat

How to name mmproj-*.gguf?

by Dunc4n1dah0 - opened May 17

Discussion

Dunc4n1dah0

May 17

Can someone tell me please, how TF should I name my mmproj-BF16.gguf?

I tried every name that came to my mind:
gemma-3-12b-it-qat-UD-Q5_K_XL.gguf

gemma-3-12b-it-mmproj-BF16.gguf -> mmproj-F16.gguf
gemma-3-12b-it-mmproj-F16.gguf -> mmproj-F16.gguf
gemma-3-12b-it-qat-UD-Q5_K_XL-mmproj-BF16.gguf -> mmproj-BF16.gguf
gemma-3-12b-it-qat-UD-Q5_K_XL-mmproj-F16.gguf -> mmproj-F16.gguf
gemma-3-12b-it-qat-mmproj-BF16.gguf -> mmproj-BF16.gguf
gemma-3-12b-it-qat-mmproj-F16.gguf -> mmproj-F16.gguf
mmproj-BF16.gguf
mmproj-F16.gguf

I even downloaded F16 version.

Still in ComfyUI:
gguf qtypes: F32 (289), Q6_K (87), Q5_K (230), Q4_K (20)
Attempting to recreate sentencepiece tokenizer from GGUF file metadata...
Created tokenizer with vocab size of 262208
Dequantizing token_embd.weight to prevent runtime OOM.
clip missing: ['multi_modal_projector.mm_input_projection_weight', 'multi_modal_projector.mm_soft_emb_norm.weight', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.embeddings.patch_embedding.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.weight',
...

tefaworld

Jul 5

same thing no matter what i do i still get that error with these models i think its corrupted

DesignDeejay

Jul 13

try mmproj-model-f16-12B.gguf - mmproj-model-Bf16-12B.gguf

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment