Instructions to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF 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 danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf danlou/relay-v0.1-Mistral-Nemo-2407-GGUF: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 danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf danlou/relay-v0.1-Mistral-Nemo-2407-GGUF: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 danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M

Use Docker

docker model run hf.co/danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "danlou/relay-v0.1-Mistral-Nemo-2407-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danlou/relay-v0.1-Mistral-Nemo-2407-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M

Ollama
How to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF with Ollama:
```
ollama run hf.co/danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
```

Unsloth Studio

How to use danlou/relay-v0.1-Mistral-Nemo-2407-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 danlou/relay-v0.1-Mistral-Nemo-2407-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 danlou/relay-v0.1-Mistral-Nemo-2407-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for danlou/relay-v0.1-Mistral-Nemo-2407-GGUF to start chatting

Docker Model Runner
How to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF with Docker Model Runner:
```
docker model run hf.co/danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M
```

Lemonade

How to use danlou/relay-v0.1-Mistral-Nemo-2407-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull danlou/relay-v0.1-Mistral-Nemo-2407-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.relay-v0.1-Mistral-Nemo-2407-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

📟 Relay v0.1 (Mistral Nemo 2407)

This model page includes GGUF versions of relay-v0.1-Mistral-Nemo-2407. For more details about this model, please see that model page.

Note: If you have access to a CUDA GPU, it's highly recommended you use the main version (HF) of the model with the relaylm.py script, which supports better use of commands (e.g., system messages). The relaylm.py script also supports 4bit and 8bit bitsandbytes quants.