Instructions to use chatpdflocal/llama3.1-8b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chatpdflocal/llama3.1-8b-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chatpdflocal/llama3.1-8b-gguf", dtype="auto")

llama-cpp-python

How to use chatpdflocal/llama3.1-8b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="chatpdflocal/llama3.1-8b-gguf",
	filename="ggml-model-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use chatpdflocal/llama3.1-8b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chatpdflocal/llama3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chatpdflocal/llama3.1-8b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf chatpdflocal/llama3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf chatpdflocal/llama3.1-8b-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 chatpdflocal/llama3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf chatpdflocal/llama3.1-8b-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 chatpdflocal/llama3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf chatpdflocal/llama3.1-8b-gguf:Q4_K_M

Use Docker

docker model run hf.co/chatpdflocal/llama3.1-8b-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use chatpdflocal/llama3.1-8b-gguf with Ollama:
```
ollama run hf.co/chatpdflocal/llama3.1-8b-gguf:Q4_K_M
```

Unsloth Studio new

How to use chatpdflocal/llama3.1-8b-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 chatpdflocal/llama3.1-8b-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 chatpdflocal/llama3.1-8b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for chatpdflocal/llama3.1-8b-gguf to start chatting

Docker Model Runner
How to use chatpdflocal/llama3.1-8b-gguf with Docker Model Runner:
```
docker model run hf.co/chatpdflocal/llama3.1-8b-gguf:Q4_K_M
```

Lemonade

How to use chatpdflocal/llama3.1-8b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chatpdflocal/llama3.1-8b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama3.1-8b-gguf-Q4_K_M

List all available models

lemonade list

Llama3.1 8b Instruct GGUF format models which can be runned on the PCs of MacOS, Windows or Linux, Cell phones and smaller devices.

This repo focuses on the available and excellent tiny LLMs which can be easily runned for chatting PDFs on MacOS, balancing the LLM's effect and inference speed.

Useful local intelligent documents assistant AI tools:

MyDocs is a desktop App which supports Windows and MacOS, and especially for professionals who demand absolute privacy. 100% local processing ensuring total documents sovereignty and zero-cloud dependency.

If you are using Zotero for managing and reading your personal PDFs, PapersGPT is a free plugin which can assist you to chat PDFs effectively by your local llama3.1.

You can download the beautiful ChatPDFLocal MacOS app from here, load one or batch PDF files at will, and quickly experience the effect of the model through chat reading.
The default model used by local LLM is ggml-model-Q3_K_M.gguf, you can also load any customerized open source model that suits your Mac configuration size by inputing huggingface repo.

Enjoy, thank you!

Downloads last month: 1,230

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support