Instructions to use google/gemma-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-7b-GGUF",
	filename="gemma-7b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use google/gemma-7b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-7b-GGUF
# Run inference directly in the terminal:
llama-cli -hf google/gemma-7b-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-7b-GGUF
# Run inference directly in the terminal:
llama-cli -hf google/gemma-7b-GGUF

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 google/gemma-7b-GGUF
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-7b-GGUF

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 google/gemma-7b-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-7b-GGUF

Use Docker

docker model run hf.co/google/gemma-7b-GGUF

LM Studio
Jan
Ollama
How to use google/gemma-7b-GGUF with Ollama:
```
ollama run hf.co/google/gemma-7b-GGUF
```

Unsloth Studio new

How to use google/gemma-7b-GGUF 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 google/gemma-7b-GGUF 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 google/gemma-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for google/gemma-7b-GGUF to start chatting

Docker Model Runner
How to use google/gemma-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/google/gemma-7b-GGUF
```

Lemonade

How to use google/gemma-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-7b-GGUF

Run and chat with the model

lemonade run user.gemma-7b-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Error: pull model manifest ollama

by kudukudu - opened Oct 21, 2024

Discussion

kudukudu

Oct 21, 2024

Hi, I try to use the model with Ollama according to https://huggingface.co/docs/hub/ollama but it is not working.

command :
ollama run hf.co/google/gemma-7b-GGUF

result:

pulling manifest 
Error: pull model manifest: Get "Authentication%!r(MISSING)equired?nonce=VZsAKGnamjCp-giE0xXapw&scope=&service=&ts=1729508446": unsupported protocol scheme ""

lkv

Google org May 28, 2025

Hi @kudukudu ,

when trying to use ollama run hf.co/google/gemma-7b-GGUF. This often happens because of how Ollama handles direct Hugging Face URLs, especially for gated models.

The most reliable way to get Gemma running with Ollama is to use the models directly from Ollama's official model library. These models are pre-configured and optimized for Ollama's ecosystem.

Instead of: ollama run hf.co/google/gemma-7b-GGUF

ollama run gemma:7b

Ollama maintains its own comprehensive library of popular models. When you use a tag like gemma:7b, Ollama knows to pull the appropriate Gemma 7B model directly from its own verified sources, by passing any complexities associated with directly parsing Hugging Face URLs or handling gated model access tokens in that specific context. Kindly try and let us know if you have any concerns.

Thank you.

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