Instructions to use cassioblaz/gemma3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cassioblaz/gemma3 with Transformers:

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

pipe = pipeline("text-generation", model="cassioblaz/gemma3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cassioblaz/gemma3")
model = AutoModelForCausalLM.from_pretrained("cassioblaz/gemma3")
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]:]))

llama-cpp-python

How to use cassioblaz/gemma3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cassioblaz/gemma3",
	filename="gemma3.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cassioblaz/gemma3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cassioblaz/gemma3:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cassioblaz/gemma3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cassioblaz/gemma3:Q8_0
# Run inference directly in the terminal:
llama-cli -hf cassioblaz/gemma3:Q8_0

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 cassioblaz/gemma3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf cassioblaz/gemma3:Q8_0

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 cassioblaz/gemma3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cassioblaz/gemma3:Q8_0

Use Docker

docker model run hf.co/cassioblaz/gemma3:Q8_0

LM Studio
Jan

vLLM

How to use cassioblaz/gemma3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cassioblaz/gemma3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cassioblaz/gemma3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cassioblaz/gemma3:Q8_0

SGLang

How to use cassioblaz/gemma3 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 "cassioblaz/gemma3" \
    --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": "cassioblaz/gemma3",
		"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 "cassioblaz/gemma3" \
        --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": "cassioblaz/gemma3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use cassioblaz/gemma3 with Ollama:
```
ollama run hf.co/cassioblaz/gemma3:Q8_0
```

Unsloth Studio new

How to use cassioblaz/gemma3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cassioblaz/gemma3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for cassioblaz/gemma3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cassioblaz/gemma3 to start chatting

Docker Model Runner
How to use cassioblaz/gemma3 with Docker Model Runner:
```
docker model run hf.co/cassioblaz/gemma3:Q8_0
```

Lemonade

How to use cassioblaz/gemma3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cassioblaz/gemma3:Q8_0

Run and chat with the model

lemonade run user.gemma3-Q8_0

List all available models

lemonade list

cassioblaz commited on Mar 27, 2025

Commit

6aaa4b7

verified ·

1 Parent(s): 707499d

(Trained with Unsloth)

Browse files

Files changed (3) hide show

config.json +37 -0
generation_config.json +8 -0
tokenizer.model +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 34,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 1024,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
+  "vocab_size": 262208
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074