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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/gemma3",
	filename="gemma-3-12b-it-q2_k.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cortexso/gemma3 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 cortexso/gemma3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/gemma3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf cortexso/gemma3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf cortexso/gemma3:Q4_K_M

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 cortexso/gemma3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/gemma3:Q4_K_M

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 cortexso/gemma3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/gemma3:Q4_K_M

Use Docker

docker model run hf.co/cortexso/gemma3:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/gemma3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/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": "cortexso/gemma3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/gemma3:Q4_K_M

Ollama
How to use cortexso/gemma3 with Ollama:
```
ollama run hf.co/cortexso/gemma3:Q4_K_M
```

Unsloth Studio

How to use cortexso/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 cortexso/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 cortexso/gemma3 to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use cortexso/gemma3 with Docker Model Runner:
```
docker model run hf.co/cortexso/gemma3:Q4_K_M
```

Lemonade

How to use cortexso/gemma3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/gemma3:Q4_K_M

Run and chat with the model

lemonade run user.gemma3-Q4_K_M

List all available models

lemonade list

jan-hq commited on Mar 12, 2025

Commit

43f7942

verified ·

1 Parent(s): 4d767ba

Upload folder using huggingface_hub

Browse files

Files changed (11) hide show

.gitattributes +10 -0
gemma-3-27b-it-q2_k.gguf +3 -0
gemma-3-27b-it-q3_k_l.gguf +3 -0
gemma-3-27b-it-q3_k_m.gguf +3 -0
gemma-3-27b-it-q3_k_s.gguf +3 -0
gemma-3-27b-it-q4_k_m.gguf +3 -0
gemma-3-27b-it-q4_k_s.gguf +3 -0
gemma-3-27b-it-q5_k_m.gguf +3 -0
gemma-3-27b-it-q5_k_s.gguf +3 -0
gemma-3-27b-it-q6_k.gguf +3 -0
gemma-3-27b-it-q8_0.gguf +3 -0

@@ -63,3 +63,13 @@ gemma-3-1b-it-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 gemma-3-1b-it-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-27b-it-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:14dc88ca174461c69f644c7073fa56ad9f8dc729e112f9eac0af21a60c2bda13
+size 10503436576

+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd1e9e98cddafee1b0a8a5f3cc8ef4874c450929548d1ee2ceb179b053d5ad7
+size 14543178016

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1d85cd66e05ea15c68f12a898e23d8f62eaf90ae6ef9ce6aad4a5d31e90970
+size 13437356320

+version https://git-lfs.github.com/spec/v1
+oid sha256:28c85ff8502a07066faeb127ee242ca75d6c3e877722823dfea7f56696dcb2b4
+size 12167330080

+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a908362ad8823e535d7d011572bc90a60ba78beb6182bdf93d6884fc8aa2df
+size 16546404640

+version https://git-lfs.github.com/spec/v1
+oid sha256:414a0def93046f607079484c91d248c347186943dff190330f12cc97f152b9ff
+size 15673772320

+version https://git-lfs.github.com/spec/v1
+oid sha256:998ca949e7d84dad815a93d3fefb69c42ca8a81a9787a816378a1eca3be1c367
+size 19271391520

+version https://git-lfs.github.com/spec/v1
+oid sha256:19722df4fa90e3ce0b19872aa29f75f9c430c1d01537b8546c73a25e3e2183ff
+size 18766907680

+version https://git-lfs.github.com/spec/v1
+oid sha256:6666576648e100df17da653822852a2e14cac0d69ca611b6d3da4e5743fb0ce9
+size 22166690080

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3094909dec44542adb6e5d1092716321f466ed16450d0624353c1dee5619ff4
+size 28707604768

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

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

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

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