Instructions to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled",
	filename="qwen2.5-coder-3b-instruct.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled: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 ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled: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 ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

Use Docker

docker model run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

LM Studio
Jan

vLLM

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

Ollama
How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with Ollama:
```
ollama run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
```

Unsloth Studio

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled 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 ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled 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 ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled to start chatting

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled: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": "ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled: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 ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with Docker Model Runner:
```
docker model run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M
```

Lemonade

How to use ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled:Q4_K_M

Run and chat with the model

lemonade run user.qwen2.5-coder-3b-claude_opus_4.6-distilled-Q4_K_M

List all available models

lemonade list

🌟 Qwen2.5-Coder-3B — Claude Opus 4.6 Reasoning Distilled

A compact, fast, locally-runnable coding model fine-tuned on top of Qwen2.5-Coder-3B-Instruct using high-quality reasoning trajectories distilled from Claude 4.6 Opus. Designed to run efficiently on consumer hardware with as little as 4GB VRAM at ~88 tokens/sec.

💡 Model Introduction

Qwen2.5-Coder-3B-Claude-Opus-4.6-Distilled combines the strong code generation foundation of Qwen2.5-Coder with the structured, step-by-step reasoning style of Claude 4.6 Opus. Through Supervised Fine-Tuning (SFT) with LoRA, the model learns to think through problems carefully inside <think> tags before delivering precise, well-structured answers.

Unlike larger distilled models, this 3B model is built for real local inference — fast, private, and fits comfortably in 4GB VRAM.

🧠 Reasoning Style

The model adopts Claude Opus's structured reasoning pattern:

<think>
Let me analyze this carefully.

1. Identify the core objective.
2. Break down into subcomponents.
3. Consider edge cases and constraints.
4. Formulate and verify the solution.
</think>

[Final clean answer here]

🗺️ Training Pipeline

Base Model (Qwen/Qwen2.5-Coder-3B-Instruct)
 │
 ▼
Supervised Fine-Tuning (SFT) + LoRA (r=16)
 │  • 3,209 high-quality Claude reasoning samples
 │  • Unsloth 2x faster training
 │  • 1 epoch on T4 GPU (~46 mins)
 │  • Final loss: 0.88
 ▼
Qwen2.5-Coder-3B-Claude-Opus-4.6-Distilled

📋 Training Details

Parameter	Value
Base Model	Qwen/Qwen2.5-Coder-3B-Instruct
Framework	Unsloth 2026.3
LoRA rank	16
LoRA alpha	16
Trainable params	29,933,568 (0.96%)
Batch size	16 (4 × 4 grad accum)
Learning rate	2e-4
Epochs	1
Max seq length	4096
Final train loss	0.88
GPU	Tesla T4 (16GB)
Training time	~46 mins

📚 Datasets Used

Dataset	Samples	Purpose
nohurry/Opus-4.6-Reasoning-3000x-filtered	2,326	Claude 4.6 Opus reasoning trajectories
TeichAI/claude-4.5-opus-high-reasoning-250x	250	High-intensity structured reasoning
Jackrong/Qwen3.5-reasoning-700x	633	Step-by-step reasoning diversity
Total	3,209

🚀 Running Locally

Via Ollama (easiest)

ollama run hf.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled

Via llama.cpp (for GPU acceleration)

./llama-cli.exe \
  -m qwen2.5-coder-3b-claude_opus_4.6-distilled.Q4_K_M.gguf \
  -ngl 99 \
  --flash-attn on \
  --jinja \
  -cnv \
  --repeat-penalty 1.1 \
  -p "You are a helpful assistant that thinks step by step."

🌟 Core Capabilities

Structured Reasoning — thinks through problems step by step in <think> blocks before answering
Code Generation — built on Qwen2.5-Coder, strong at Python, JavaScript, algorithms
Math & Logic — correctly solves multi-step problems with verification
Fast Local Inference — 88 t/s on RTX 3050 4GB, fully GPU-accelerated

⚡ Hardware Requirements

Quantization	VRAM	Speed (RTX 3050)
Q4_K_M (this file)	~2.1 GB	~88 t/s
Q3_K_M	~1.7 GB	~95 t/s
Q8_0	~3.3 GB	~70 t/s

Runs comfortably on 4GB VRAM laptops and desktops.

⚠️ Limitations

3B scale — will struggle with very long multi-file code generation or complex system design
1 epoch training — reasoning style is distilled but not as deep as larger models
Hallucination risk — like all LLMs, may produce incorrect facts; always verify outputs

🙏 Acknowledgements

Unsloth AI for making fine-tuning accessible on consumer hardware
nohurry, TeichAI, and Jackrong for the high-quality distillation datasets
Qwen team for the excellent Qwen2.5-Coder base model

📖 Citation

@misc{ryzdfm_qwen25coder_claude_distilled,
  title        = {Qwen2.5-Coder-3B Claude Opus 4.6 Reasoning Distilled},
  author       = {ryzdfm},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled}}
}

Downloads last month: 3,274

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B