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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QomSSLab/gemma-3-12b-it")
model = AutoModelForCausalLM.from_pretrained("QomSSLab/gemma-3-12b-it", device_map="auto")
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 QomSSLab/gemma-3-12b-it with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

QomSSLab commited on Sep 25, 2025

Commit

7656ff5

verified ·

1 Parent(s): b00f116

Upload Gemma3ForConditionalGeneration

Browse files

Files changed (7) hide show

config.json +3 -3
model-00001-of-00005.safetensors +3 -0
model-00002-of-00005.safetensors +3 -0
model-00003-of-00005.safetensors +3 -0
model-00004-of-00005.safetensors +3 -0
model-00005-of-00005.safetensors +3 -0
model.safetensors.index.json +0 -0

config.json CHANGED Viewed

@@ -3,7 +3,7 @@
     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
-  "dtype": "float32",
   "eoi_token_index": 256000,
   "eos_token_id": [
     1,
@@ -18,7 +18,7 @@
     "attention_bias": false,
     "attention_dropout": 0.0,
     "attn_logit_softcapping": null,
-    "dtype": "float32",
     "final_logit_softcapping": null,
     "head_dim": 256,
     "hidden_activation": "gelu_pytorch_tanh",
@@ -95,7 +95,7 @@
   "transformers_version": "4.56.0",
   "vision_config": {
     "attention_dropout": 0.0,
-    "dtype": "float32",
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "image_size": 896,

     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
+  "dtype": "bfloat16",
   "eoi_token_index": 256000,
   "eos_token_id": [
     1,
     "attention_bias": false,
     "attention_dropout": 0.0,
     "attn_logit_softcapping": null,
+    "dtype": "bfloat16",
     "final_logit_softcapping": null,
     "head_dim": 256,
     "hidden_activation": "gelu_pytorch_tanh",
   "transformers_version": "4.56.0",
   "vision_config": {
     "attention_dropout": 0.0,
+    "dtype": "bfloat16",
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "image_size": 896,

model-00001-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
+size 4979902192

model-00002-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:891bd54eed03cba9ee1e705533a02a8217fcc29f356e4a1f53e5fd0d178883ad
+size 4931296592

model-00003-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cee411d9d57324e50ce064a192cc5a858276d508611b12fc599e0c9767112e0
+size 4931296656

model-00004-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc75a29a730c9e743cad013feda3b0991a913fafe787c58a1c6e20afad97723
+size 4931296656

model-00005-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed14bd4908c98fed9f61e8cd410167e0846de9abd78e0452ab092072e5d9252d
+size 4601000928

model.safetensors.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff