Instructions to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deltakitsune/Nanbeige-4.1-Python-DeepThink-3B",
	filename="nanbeige4.1-python-deepthink-fp16.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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
# Run inference directly in the terminal:
llama-cli -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
# Run inference directly in the terminal:
llama-cli -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
# Run inference directly in the terminal:
./llama-cli -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

Use Docker

docker model run hf.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

LM Studio
Jan

vLLM

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deltakitsune/Nanbeige-4.1-Python-DeepThink-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deltakitsune/Nanbeige-4.1-Python-DeepThink-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

Ollama
How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with Ollama:
```
ollama run hf.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
```

Unsloth Studio new

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B 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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B 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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deltakitsune/Nanbeige-4.1-Python-DeepThink-3B to start chatting

Pi new

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

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": "deltakitsune/Nanbeige-4.1-Python-DeepThink-3B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

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 deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

Run Hermes

hermes

Docker Model Runner
How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with Docker Model Runner:
```
docker model run hf.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B
```

Lemonade

How to use deltakitsune/Nanbeige-4.1-Python-DeepThink-3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deltakitsune/Nanbeige-4.1-Python-DeepThink-3B

Run and chat with the model

lemonade run user.Nanbeige-4.1-Python-DeepThink-3B-{{QUANT_TAG}}

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Nanbeige 4.1 Python DeepThink - 3B

Fine-tuned version of Nanbeige/Nanbeige4.1-3B specialized for Python code generation with direct, focused output.

Version: E1 (Experiment 1)
Training Focus: Code accuracy and clean output format
Status: Production-ready for direct code generation tasks

Model Description

This model was fine-tuned using LoRA on 45,757 examples (84% Python code, 16% mathematical reasoning) to specialize in Python code generation. It achieves 87.4% token-level accuracy while providing clean, direct responses optimized for production use.

Training Details

Base Model: Nanbeige/Nanbeige4.1-3B (3B parameters)
Method: LoRA (r=16, alpha=16)
Trainable Parameters: 28.4M (0.72%)
Training Time: ~16 hours on RTX 5060 Ti 16GB
Datasets: Magicoder-OSS-Instruct-75K (Python), GSM8K (reasoning)
Framework: Transformers + PEFT

Performance Improvements

Metric	Baseline	Fine-tuned	Change
Loss	1.04	0.45	-57%
Token Accuracy	76.3%	87.4%	+11.1 pts
Entropy	0.78	0.44	-44%

Key Features

✅ Direct Output Format - Clean code responses without verbose preambles
✅ High Accuracy - 87% token-level accuracy on Python tasks
✅ Fast Inference - Optimized for quick responses
⚠️ Suppressed Chain-of-Thought - E1 focuses on direct answers (reasoning occurs internally but isn't narrated)

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    'deltakitsune/Nanbeige-4.1-Python-DeepThink-3B',
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    'deltakitsune/Nanbeige-4.1-Python-DeepThink-3B',
    trust_remote_code=True
)

prompt = 'Write a Python function to validate email addresses'
inputs = tokenizer(prompt, return_tensors='pt')
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs[0]))

Ollama

# Pull from Ollama registry
ollama pull fauxpaslife/nanbeige4.1-python-deepthink:3b

# Run
ollama run fauxpaslife/nanbeige4.1-python-deepthink:3b

llama.cpp

# Download GGUF
wget https://huggingface.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B/resolve/main/nanbeige4.1-python-deepthink-q8.gguf

# Run
./llama-cli -m nanbeige4.1-python-deepthink-q8.gguf -p \"Write a binary search function\"

File Structure

*.safetensors - Merged model weights (Transformers)
config.json - Model configuration
```
okenizer.json - Tokenizer files
```
anbeige4.1-python-deepthink-fp16.gguf - Full precision GGUF (7.9GB)
anbeige4.1-python-deepthink-q8.gguf - 8-bit quantized GGUF (4.2GB)

Best Use Cases

Direct Python code generation
Algorithm implementations
Flask/FastAPI endpoint creation
Code debugging with concise explanations
Production codebases requiring deterministic output

When to Use Base Model Instead

Complex problems requiring visible reasoning
Exploring multiple solution approaches
Educational explanations with thought process
Research/debugging requiring transparency

Training Notes

E1 focused on direct output format. Training data contained no chain-of-thought examples, resulting in suppressed tag behavior. Internal reasoning capability is preserved (evidenced by accuracy gains), but output format is optimized for production code generation.

E2 Development: Next iteration will reintroduce chain-of-thought reasoning while maintaining code quality.

Citation

@misc{nanbeige-python-deepthink-e1,
  title={Nanbeige 4.1 Python DeepThink 3B},
  author={deltakitsune},
  year={2026},
  publisher={HuggingFace},
  url={https://huggingface.co/deltakitsune/Nanbeige-4.1-Python-DeepThink-3B}
}