Instructions to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF",
	filename="nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS/nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS-00001-of-00008.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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 featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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 featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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 featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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": "featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M

Ollama
How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with Ollama:
```
ollama run hf.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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 featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-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 featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF to start chatting

Docker Model Runner
How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with Docker Model Runner:
```
docker model run hf.co/featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M
```

Lemonade

How to use featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.nvidia-Llama3-ChatQA-1.5-70B-GGUF-Q4_K_M

List all available models

lemonade list

nvidia/Llama3-ChatQA-1.5-70B GGUF Quantizations 🚀

Optimized GGUF quantization files for enhanced model performance

Powered by Featherless AI - run any model you'd like for a simple small fee.

Available Quantizations 📊

Quantization Type	File	Size
IQ4_XS	nvidia-Llama3-ChatQA-1.5-70B-IQ4_XS	36496.80 MB (folder)
Q2_K	nvidia-Llama3-ChatQA-1.5-70B-Q2_K	25153.26 MB (folder)
Q3_K_L	nvidia-Llama3-ChatQA-1.5-70B-Q3_K_L	35420.03 MB (folder)
Q3_K_M	nvidia-Llama3-ChatQA-1.5-70B-Q3_K_M	32680.03 MB (folder)
Q3_K_S	nvidia-Llama3-ChatQA-1.5-70B-Q3_K_S	29480.03 MB (folder)
Q4_K_M	nvidia-Llama3-ChatQA-1.5-70B-Q4_K_M	40550.61 MB (folder)
Q4_K_S	nvidia-Llama3-ChatQA-1.5-70B-Q4_K_S	38478.11 MB (folder)
Q5_K_M	nvidia-Llama3-ChatQA-1.5-70B-Q5_K_M	47635.86 MB (folder)
Q5_K_S	nvidia-Llama3-ChatQA-1.5-70B-Q5_K_S	46403.36 MB (folder)
Q6_K	nvidia-Llama3-ChatQA-1.5-70B-Q6_K	55206.44 MB (folder)
Q8_0	nvidia-Llama3-ChatQA-1.5-70B-Q8_0	71501.78 MB (folder)

⚡ Powered by Featherless AI

Key Features

🔥 Instant Hosting - Deploy any Llama model on HuggingFace instantly
🛠️ Zero Infrastructure - No server setup or maintenance required
📚 Vast Compatibility - Support for 2400+ models and counting
💎 Affordable Pricing - Starting at just $10/month

Links:
Get Started | Documentation | Models

Downloads last month: 35

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for featherless-ai-quants/nvidia-Llama3-ChatQA-1.5-70B-GGUF

Base model

nvidia/Llama3-ChatQA-1.5-70B

Quantized

(5)

this model