himanshu231204/ hk-devbrain

51 Downloads Updated 1 month ago

HK-DevBrain is a lightweight AI developer assistant built on Llama 3.2 (3B) for code generation, math reasoning, and technical documentation. Optimized for local inference with Ollama.

tools

ollama run himanshu231204/hk-devbrain:v3

curl http://localhost:11434/api/chat \
  -d '{
    "model": "himanshu231204/hk-devbrain:v3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='himanshu231204/hk-devbrain:v3',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'himanshu231204/hk-devbrain:v3',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model himanshu231204/hk-devbrain:v3

Codex

Codex ollama launch codex --model himanshu231204/hk-devbrain:v3

OpenCode

OpenCode ollama launch opencode --model himanshu231204/hk-devbrain:v3

OpenClaw

OpenClaw ollama launch openclaw --model himanshu231204/hk-devbrain:v3

Models

Name

1 model

Size

Context

Input

hk-devbrain:v3

2.0GB · 128K context window · Text · 1 month ago

hk-devbrain:v3

2.0GB

128K

Text

Readme

🧠 HK-DevBrain

HK-DevBrain is a lightweight AI developer assistant built on Llama 3.2 (3B) and optimized for local inference using Ollama.

It helps developers with:

💻 Code generation
📐 Mathematical reasoning
📝 Technical documentation
📦 README generation for projects

🚀 Run the Model

ollama run himanshu231204/hk-devbrain:v3

⚡ Features

Multi-language code generation (Python, JavaScript, TypeScript, C++, Go, etc.)
Step-by-step math problem solving
Professional README and documentation generation
Lightweight (~2GB model size)
Fast local inference
Runs fully offline with Ollama

💻 Example Prompts

Code Generation

Write a Python function to implement binary search

Mathematics

Solve the derivative of 5x^2 + 3x

Documentation

Generate a README for a FastAPI project

🧩 Model Details

Base Model: Llama 3.2
Parameters: ~3B
Quantization: Q4_K_M
Size: ~2GB

📦 GitHub Repository

https://github.com/himanshu231204/hk-devbrain

👨‍💻 Author

Himanshu Kumar

🌐 Connect With Me

💼 LinkedIn: https://www.linkedin.com/in/himanshu231204

🐙 GitHub: https://github.com/himanshu231204

🐦 Twitter/X: https://twitter.com/himanshu231204

☕ Buy Me a Coffee: https://www.buymeacoffee.com/himanshu231204

⭐ If you find this model useful, consider starring the GitHub repository.

# 🧠 HK-DevBrain

**HK-DevBrain** is a lightweight AI developer assistant built on **Llama 3.2 (3B)** and optimized for local inference using **Ollama**.

It helps developers with:

* 💻 Code generation
* 📐 Mathematical reasoning
* 📝 Technical documentation
* 📦 README generation for projects

---

## 🚀 Run the Model

```
ollama run himanshu231204/hk-devbrain:v3
```

---

## ⚡ Features

* Multi-language code generation (Python, JavaScript, TypeScript, C++, Go, etc.)
* Step-by-step math problem solving
* Professional README and documentation generation
* Lightweight (~2GB model size)
* Fast local inference
* Runs fully offline with Ollama

---

## 💻 Example Prompts

### Code Generation

```
Write a Python function to implement binary search
```

### Mathematics

```
Solve the derivative of 5x^2 + 3x
```

### Documentation

```
Generate a README for a FastAPI project
```

---

## 🧩 Model Details

* **Base Model:** Llama 3.2
* **Parameters:** ~3B
* **Quantization:** Q4_K_M
* **Size:** ~2GB

---

## 📦 GitHub Repository

https://github.com/himanshu231204/hk-devbrain

---

## 👨‍💻 Author

**Himanshu Kumar**

---

## 🌐 Connect With Me

💼 LinkedIn: https://www.linkedin.com/in/himanshu231204

🐙 GitHub: https://github.com/himanshu231204

🐦 Twitter/X: https://twitter.com/himanshu231204

☕ Buy Me a Coffee: https://www.buymeacoffee.com/himanshu231204

---

⭐ If you find this model useful, consider starring the GitHub repository.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)