Instructions to use modularai/Llama-3.1-8B-Instruct-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 modularai/Llama-3.1-8B-Instruct-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 modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf modularai/Llama-3.1-8B-Instruct-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 modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf modularai/Llama-3.1-8B-Instruct-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 modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf modularai/Llama-3.1-8B-Instruct-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 modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use modularai/Llama-3.1-8B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modularai/Llama-3.1-8B-Instruct-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": "modularai/Llama-3.1-8B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M

Ollama
How to use modularai/Llama-3.1-8B-Instruct-GGUF with Ollama:
```
ollama run hf.co/modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use modularai/Llama-3.1-8B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use modularai/Llama-3.1-8B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull modularai/Llama-3.1-8B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.1-8B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Working with only these models?

by supercharge19 - opened Jan 3, 2025

Discussion

supercharge19

Jan 3, 2025

Can magic run any model on huggingface (that transformers can run)? Or can it only run either of these models onlhy?

tbmod

Jan 13, 2025

Hey @supercharge19 ,
This HF repo is primarily for convenience to host example quantized models.

MAX Serve provides an OpenAI-compatible endpoint for any PyTorch LLM on HF.
MAX currently accelerates PyTorch LLMs you can run today with HF Transformers using LlamaForCausalLM, MistralForCausalLM and MPTForCausalLM. More models are expected to be accelerated in the future.

FYI magic is the package manager, while MAX is the platform which the models run on

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