Instructions to use LLMWildling/gemma-4-120b-a12b-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLMWildling/gemma-4-120b-a12b-coder with Transformers:

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

pipe = pipeline("text-generation", model="LLMWildling/gemma-4-120b-a12b-coder")
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("LLMWildling/gemma-4-120b-a12b-coder")
model = AutoModelForMultimodalLM.from_pretrained("LLMWildling/gemma-4-120b-a12b-coder")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLMWildling/gemma-4-120b-a12b-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLMWildling/gemma-4-120b-a12b-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMWildling/gemma-4-120b-a12b-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLMWildling/gemma-4-120b-a12b-coder

SGLang

How to use LLMWildling/gemma-4-120b-a12b-coder 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 "LLMWildling/gemma-4-120b-a12b-coder" \
    --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": "LLMWildling/gemma-4-120b-a12b-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "LLMWildling/gemma-4-120b-a12b-coder" \
        --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": "LLMWildling/gemma-4-120b-a12b-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLMWildling/gemma-4-120b-a12b-coder with Docker Model Runner:
```
docker model run hf.co/LLMWildling/gemma-4-120b-a12b-coder
```

Questions from noob

by lordfervi - opened 21 days ago

Discussion

lordfervi

21 days ago

I stumbled upon your profile by accident.

I'm wondering how you add so many parameters to these models—is it a lot of fine-tuning?

My DGX Spark is supposed to arrive soon, and I'm really looking forward to seeing if the model is significantly better.

LLMWildling

Owner 20 days ago

@lordfervi ive been going at this for 2 years now, its pretty complicated and I still work on perfecting it. do you want me to make you one? feedback is super welcome. enjoy.

lordfervi

20 days ago

@LLMWildling
Let's just say this, we'll stay in touch :)

People usually do various types of model optimization. Your models look like they do some fine-tuning.

I'm afraid we'll reach a point where you'll have enterprise models in the cloud (OpenAI, Claude), some large open-source models (like DeepSeek), but not for consumers (too expensive), you'll have small models (like Gemma), but very few mid-tier models (like Mistral Small 4, GPT-OSS, etc.).

If it's possible to "easily" improve AI models, I think it's revolutionary.

I accidentally found your profile and see that you've made a lot of models much larger. I'm wondering if it works correctly and so on.

Unfortunately, I don't have the DGX Spark for now (I hope I'll have it next week). I'll let you know when I can test it.

Maybe in the future you'll manage to slightly (even not significantly) tune Mistral Small 4 ;)

LLMWildling

Owner 20 days ago

I just checked my pipeline and but pretty sure it's pre/post training, the full run. I use my own optimizer to speed things up.

"If it's possible to "easily" improve AI models, I think it's revolutionary." - thats the idea, but things take time to perfect. so any feedback from this community is welcome, I have a lot more coming.

Mistral Small 4 - do you want a bigger version? @lordfevi

lordfervi

17 days ago

@LLMWildling

That's interesting.

I don't need it right now, but once I get the machine, I'll test the current models :)

It's just that what you're doing is interesting, and that's why I'm asking :)

lordfervi

12 days ago

@LLMWildling

I have a DGX Spark for testing.

I have an alternative question. Can you try creating powerful models on DiffusionGemma?

It’s Gemma 4, which works on the principle of diffusion. In short—it’s worse (in benchmarks), but much faster. It’s more of a demo, really.

I’ll be checking out your models, but the DGX Spark is very slow over Wi-Fi.

LLMWildling

Owner 12 days ago

@lordfervi its possible it depends on if there is support in transformers for it. its possible. Currently I am stuck in quantization hell, im loosing accuracy going from bf16 to mxfp4/nvfp4 . im trying to fix that first and I can take a look at it.

LLMWildling

Owner 11 days ago

I just had a ok run with nvfp4. let me see what I can do @lordfevi

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