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

Libraries

How to use PsalMonster/gemma-3-12b-it-textonly with Transformers:

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

pipe = pipeline("text-generation", model="PsalMonster/gemma-3-12b-it-textonly")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PsalMonster/gemma-3-12b-it-textonly")
model = AutoModelForCausalLM.from_pretrained("PsalMonster/gemma-3-12b-it-textonly")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PsalMonster/gemma-3-12b-it-textonly with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PsalMonster/gemma-3-12b-it-textonly"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PsalMonster/gemma-3-12b-it-textonly",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PsalMonster/gemma-3-12b-it-textonly

SGLang

How to use PsalMonster/gemma-3-12b-it-textonly 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 "PsalMonster/gemma-3-12b-it-textonly" \
    --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": "PsalMonster/gemma-3-12b-it-textonly",
		"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 "PsalMonster/gemma-3-12b-it-textonly" \
        --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": "PsalMonster/gemma-3-12b-it-textonly",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PsalMonster/gemma-3-12b-it-textonly with Docker Model Runner:
```
docker model run hf.co/PsalMonster/gemma-3-12b-it-textonly
```

gemma-3-12b-it (text-only)

A text-only derivative of google/gemma-3-12b-it, with the language model extracted from the multimodal checkpoint. The multimodal wrapper (vision tower + multi-modal projector) is removed and the model is reconstructed as a pure Gemma3ForCausalLM (model_type: gemma3_text).

Why

The original multimodal gemma-3 applies bidirectional attention over image tokens (mm-prefix), which prevents it from loading on vLLM's FlashInfer backend. The text-only form clears the mm-prefix flag, so it runs on the FlashInfer / KV-compaction pipeline.

How it was extracted

Keep only language_model.* weights, strip the prefix to model.*
Drop vision_tower.* and multi_modal_projector.*
config = the original text_config (48 layers, sliding_window=1024, 5:1 hybrid)
tokenizer and other files are unchanged from the original

Weight values are identical to the original (lossless for the language model). Image inputs are not supported.

License

This is a Gemma derivative. Use is governed by the Gemma Terms of Use and the Prohibited Use Policy. "Gemma" is a trademark of Google LLC.

Downloads last month: 21

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for PsalMonster/gemma-3-12b-it-textonly

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Finetuned

(360)

this model