Instructions to use palusi/Qwen2-0.5B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use palusi/Qwen2-0.5B-Instruct-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("palusi/Qwen2-0.5B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use palusi/Qwen2-0.5B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="palusi/Qwen2-0.5B-Instruct-GGUF",
	filename="Qwen2-0.5B-Instruct-F16.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 palusi/Qwen2-0.5B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf palusi/Qwen2-0.5B-Instruct-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 palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf palusi/Qwen2-0.5B-Instruct-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 palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf palusi/Qwen2-0.5B-Instruct-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 palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use palusi/Qwen2-0.5B-Instruct-GGUF with Ollama:
```
ollama run hf.co/palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use palusi/Qwen2-0.5B-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 palusi/Qwen2-0.5B-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 palusi/Qwen2-0.5B-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 palusi/Qwen2-0.5B-Instruct-GGUF to start chatting

Docker Model Runner
How to use palusi/Qwen2-0.5B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use palusi/Qwen2-0.5B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull palusi/Qwen2-0.5B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2-0.5B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2-0.5B-Instruct-GGUF

Summary

Quantized Version of Qwen/Qwen2-0.5B-Instruct.

Chat template

{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>

Models

Name	Quant method	Bits	Size
Qwen2-0.5B-Instruct-Q2_K.gguf	Q2_K	2	339MB
Qwen2-0.5B-Instruct-Q3_K_L.gguf	Q3_K_L	3	369MB
Qwen2-0.5B-Instruct-Q3_K_M.gguf	Q3_K_M	3	355MB
Qwen2-0.5B-Instruct-Q3_K_S.gguf	Q3_K_S	3	338MB
Qwen2-0.5B-Instruct-Q4_0.gguf	Q4_0	4	352MB
Qwen2-0.5B-Instruct-Q4_K_M.gguf	Q4_K_M	4	398MB
Qwen2-0.5B-Instruct-Q4_K_S.gguf	Q4_K_S	4	385MB
Qwen2-0.5B-Instruct-Q5_0.gguf	Q5_0	5	397MB
Qwen2-0.5B-Instruct-Q5_K_M.gguf	Q5_K_M	5	420MB
Qwen2-0.5B-Instruct-Q5_K_S.gguf	Q5_K_S	5	413MB
Qwen2-0.5B-Instruct-Q6_K.gguf	Q6_K	6	506MB
Qwen2-0.5B-Instruct-Q8_0.gguf	Q8_0	8	531MB

Downloads last month: 83

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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