Instructions to use Nondzu/PLLuM-8x7B-chat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nondzu/PLLuM-8x7B-chat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nondzu/PLLuM-8x7B-chat-GGUF",
	filename="PLLuM-8x7B-chat-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nondzu/PLLuM-8x7B-chat-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Nondzu/PLLuM-8x7B-chat-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 Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Nondzu/PLLuM-8x7B-chat-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 Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nondzu/PLLuM-8x7B-chat-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 Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Nondzu/PLLuM-8x7B-chat-GGUF with Ollama:
```
ollama run hf.co/Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
```

Unsloth Studio

How to use Nondzu/PLLuM-8x7B-chat-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 Nondzu/PLLuM-8x7B-chat-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 Nondzu/PLLuM-8x7B-chat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nondzu/PLLuM-8x7B-chat-GGUF to start chatting

Docker Model Runner
How to use Nondzu/PLLuM-8x7B-chat-GGUF with Docker Model Runner:
```
docker model run hf.co/Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M
```

Lemonade

How to use Nondzu/PLLuM-8x7B-chat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nondzu/PLLuM-8x7B-chat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.PLLuM-8x7B-chat-GGUF-Q4_K_M

List all available models

lemonade list

PLLuM-8x7B-chat GGUF Quantizations by Nondzu

DISCLAIMER: This is a quantized version of an existing model PLLuM-8x7B-chat. I am not the author of the original model. I am only hosting the quantized models. I do not take any responsibility for the models.

Prompt Format

Use the following prompt structure:

???

Available Files

Below is a list of available quantized model files along with their quantization type, file size, and a short description.

Filename	Quant Type	File Size	Description
PLLuM-8x7B-chat-Q2_K.gguf	Q2_K	17 GB	Very low quality but surprisingly usable.
PLLuM-8x7B-chat-Q3_K.gguf	Q3_K	21 GB	Low quality, suitable for setups with very limited RAM.
PLLuM-8x7B-chat-Q3_K_L.gguf	Q3_K_L	23 GB	High quality; recommended for quality-focused usage.
PLLuM-8x7B-chat-Q3_K_M.gguf	Q3_K_M	21 GB	Very high quality, near perfect output – recommended.
PLLuM-8x7B-chat-Q3_K_S.gguf	Q3_K_S	20 GB	Moderate quality with improved space efficiency.
PLLuM-8x7B-chat-Q4_K.gguf	Q4_K	27 GB	Good quality for standard use.
PLLuM-8x7B-chat-Q4_K_M.gguf	Q4_K_M	27 GB	Default quality for most use cases – recommended.
PLLuM-8x7B-chat-Q4_K_S.gguf	Q4_K_S	25 GB	Slightly lower quality with enhanced space savings – recommended when size is a priority.
PLLuM-8x7B-chat-Q5_0.gguf	Q5_0	31 GB	Extremely high quality – the maximum quant available.
PLLuM-8x7B-chat-Q5_K.gguf	Q5_K	31 GB	Very high quality – recommended for demanding use cases.
PLLuM-8x7B-chat-Q5_K_M.gguf	Q5_K_M	31 GB	High quality – recommended.
PLLuM-8x7B-chat-Q5_K_S.gguf	Q5_K_S	31 GB	High quality, offered as an alternative with minimal quality loss.
PLLuM-8x7B-chat-Q6_K.gguf	Q6_K	36 GB	Very high quality with quantized embed/output weights.
PLLuM-8x7B-chat-Q8_0.gguf	Q8_0	47 GB	Maximum quality quantization.

Downloading Using Hugging Face CLI

Click to view download instructions

First, ensure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Then, target a specific file to download:

huggingface-cli download Nondzu/PLLuM-8x7B-chat-GGUF --include "PLLuM-8x7B-chat-Q4_K_M.gguf" --local-dir ./

For larger files, you can specify a new local directory (e.g., PLLuM-8x7B-chat-Q8_0) or download them directly into the current directory (./).

Downloads last month: 88

GGUF

Model size

47B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for Nondzu/PLLuM-8x7B-chat-GGUF

Base model

CYFRAGOVPL/PLLuM-8x7B-chat-2412

Quantized

(6)

this model