Instructions to use oyi77/qwen2.5-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oyi77/qwen2.5-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="oyi77/qwen2.5-7b-GGUF",
	filename="qwen2.5-7b-instruct-Q4_K_M.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 oyi77/qwen2.5-7b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf oyi77/qwen2.5-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf oyi77/qwen2.5-7b-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 oyi77/qwen2.5-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf oyi77/qwen2.5-7b-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 oyi77/qwen2.5-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf oyi77/qwen2.5-7b-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 oyi77/qwen2.5-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oyi77/qwen2.5-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/oyi77/qwen2.5-7b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use oyi77/qwen2.5-7b-GGUF with Ollama:
```
ollama run hf.co/oyi77/qwen2.5-7b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use oyi77/qwen2.5-7b-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 oyi77/qwen2.5-7b-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 oyi77/qwen2.5-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for oyi77/qwen2.5-7b-GGUF to start chatting

Pi new

How to use oyi77/qwen2.5-7b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf oyi77/qwen2.5-7b-GGUF:Q4_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": "oyi77/qwen2.5-7b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use oyi77/qwen2.5-7b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf oyi77/qwen2.5-7b-GGUF:Q4_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 oyi77/qwen2.5-7b-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use oyi77/qwen2.5-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/oyi77/qwen2.5-7b-GGUF:Q4_K_M
```

Lemonade

How to use oyi77/qwen2.5-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oyi77/qwen2.5-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen2.5-7b-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-7B-Instruct GGUF

Quantized GGUF versions of Qwen/Qwen2.5-7B-Instruct for local inference.

Available Quantizations

File	Size	Quality	Use Case
`qwen2.5-7b-instruct-Q4_K_M.gguf`	~4.4GB	⭐⭐⭐⭐	Best balance — recommended
`qwen2.5-7b-instruct-Q5_K_M.gguf`	~5.1GB	⭐⭐⭐⭐⭐	Higher quality, needs more RAM
`qwen2.5-7b-instruct-Q8_0.gguf`	~7.7GB	⭐⭐⭐⭐⭐	Near-lossless, needs 10GB+ RAM

Usage

Via Ollama (Easiest)

ollama run qwen2.5:7b

Via llama.cpp

./llama-cli -m qwen2.5-7b-instruct-Q4_K_M.gguf -p "Your prompt here" -n 512

Via Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="paijo77/qwen2.5-7b-GGUF",
    filename="qwen2.5-7b-instruct-Q4_K_M.gguf",
    n_ctx=8192,
    n_gpu_layers=-1  # use GPU if available
)

response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Explain quantum computing simply"}]
)
print(response["choices"][0]["message"]["content"])

Via Open WebUI

Download the GGUF file
In Open WebUI → Models → Add model
Point to local GGUF file

Why Qwen2.5-7B?

Multilingual: English, Chinese, 29+ languages
Long context: 128K tokens natively
Coding: Excellent code generation
Math: Strong mathematical reasoning
Instruction following: Clean, structured outputs
Size: Runs on 6GB VRAM or 8GB RAM (CPU)

Hardware Requirements

Quantization	Min RAM	Min VRAM	Speed (CPU)
Q4_K_M	6GB	5GB	~15 tok/s
Q5_K_M	8GB	6GB	~12 tok/s
Q8_0	10GB	8GB	~8 tok/s

Support This Project

Quantization takes compute and time. If this helps you: 👉 https://www.tip.md/oyi77

License

Apache 2.0 — based on Qwen2.5 (Apache 2.0)

Downloads last month: 28

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for oyi77/qwen2.5-7b-GGUF

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(313)

this model