Instructions to use aaardpark/Qwen2.5-72B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aaardpark/Qwen2.5-72B-Instruct-GGUF",
	filename="Qwen2.5-72B-Instruct-aaardpark-Q3_K_M.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 aaardpark/Qwen2.5-72B-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 aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_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 aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_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 aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Use Docker

docker model run hf.co/aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

LM Studio
Jan
Ollama
How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with Ollama:
```
ollama run hf.co/aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
```

Unsloth Studio

How to use aaardpark/Qwen2.5-72B-Instruct-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 aaardpark/Qwen2.5-72B-Instruct-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 aaardpark/Qwen2.5-72B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aaardpark/Qwen2.5-72B-Instruct-GGUF to start chatting

How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M
```

Lemonade

How to use aaardpark/Qwen2.5-72B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aaardpark/Qwen2.5-72B-Instruct-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.Qwen2.5-72B-Instruct-GGUF-Q3_K_M

List all available models

lemonade list

Qwen2.5-72B-Instruct-GGUF / README.md

aaardpark

Upload README.md with huggingface_hub

a6d7cf0 verified 3 months ago

2.91 kB

license: apache-2.0
base_model: Qwen/Qwen2.5-72B-Instruct
tags:
  - quantized
  - gguf
  - 3-bit
  - qwen2
model_type: qwen2
quantized_by: aaardpark

Qwen2.5-72B-Instruct — 3-bit GGUF (aaardpark)

Qwen2.5-72B-Instruct quantized to 3-bit using a new importance-weighted quantization method. Produces significantly better quality at 3-bit than standard RTN or naive quantization approaches.

Key Results (Base Model Benchmarks)

Metric	FP16	This Quant (3-bit)	RTN 3-bit
Perplexity	2.670	3.163	3.750
GSM8K (5-shot)	90%	88%	16%
MMLU avg (5-shot)	77.6%	76.8%	73.0%
TruthfulQA	58.5%	56.9%	56.3%

Benchmarks measured on Qwen2.5-72B (base) with lm-evaluation-harness. The quantization method is identical for both base and Instruct variants.

vs Other Quantization Methods

Method	Bits	PPL (72B)	GSM8K	Notes
FP16	16	2.670	90%	Baseline
This quant	3	3.163	88%	35 GB
RTN 3-bit	3	3.750	16%	Standard rounding
GPTQ 4-bit	4	3.562*	—	25% larger file
RTN 4-bit	4	2.790	88%	45 GB
This quant (4-bit)	4	2.747	93%	Effectively lossless

*GPTQ 4-bit PPL from Qwen2.5-32B (3.562), scaled comparison.

On smaller models (7B): GPTQ 3-bit PPL = 12.576, our 3-bit PPL = 6.148. GPTQ is unusable at 3-bit; ours is not.

GGUF Perplexity (wikitext-2, llama.cpp)

Variant	PPL
Base Q8_0 (exact weights)	3.028
Base Q3_K_M (this format)	2.904
Instruct Q3_K_M	3.962

Why This Quant is Different

Standard 3-bit quantization (RTN) rounds each weight to the nearest grid point uniformly. This destroys the precise weight values that control multi-step reasoning — GSM8K drops from 90% to 16%.

Our method uses calibration data to identify which weights are critical for model quality, then allocates quantization precision accordingly. The result: 88% GSM8K at 3-bit, nearly matching FP16.

Details

Method: Importance-weighted per-group optimization
Group size: 128
Quantization time: ~20 minutes on a single GPU
GGUF format: Q3_K_M (converted via llama.cpp)
File size: 35 GB
Context: 128K tokens

How to Use

Works with llama.cpp, Ollama, LM Studio, or any GGUF-compatible runtime.

# llama.cpp
llama-cli -m Qwen2.5-72B-Instruct-aaardpark-Q3_K_M.gguf -ngl 99 -p "Hello!"

# Ollama
ollama run aaardpark/qwen2.5-72b-instruct

Chat Template

This model uses the ChatML template:

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Acknowledgments

Built on Qwen2.5-72B-Instruct by Alibaba Cloud.