🧠 Krish Mind

Krish Mind is an independent AI assistant created by Krish CS. It is designed to be helpful, intelligent, and friendly.

This repository contains the model in GGUF format, which is optimized for running on regular computers (CPUs) without needing expensive GPUs.


πŸ“¦ Available Model Files

File Name Size Best For RAM Required
krish-mind-standalone-Q4.gguf ~5 GB πŸ–₯️ Most computers, Free cloud services 8-16 GB
krish-mind-standalone.gguf ~16 GB πŸ’ͺ Powerful computers, Best quality 32+ GB

Which one should I download?

  • If you have a normal computer (8-16 GB RAM): Download the Q4 version.
  • If you have a powerful computer (32+ GB RAM): Download the Full version for best quality.

πŸš€ How to Use (Step-by-Step for Beginners)

You have 3 easy options to run Krish Mind on your computer:


Option 1: Use with Ollama (Easiest! Recommended for Beginners)

Ollama is a free app that lets you run AI models with just one click.

Steps:

  1. Download and Install Ollama:

  2. Download the Model File:

    • Click on krish-mind-standalone-Q4.gguf above
    • Click the Download button
    • Save it somewhere you can find (e.g., your Downloads folder)
  3. Create a Modelfile:

    • Open Notepad (or any text editor)
    • Type this:
      FROM ./krish-mind-standalone-Q4.gguf
      
    • Save it as Modelfile (no extension) in the same folder as the .gguf file
  4. Open Terminal/Command Prompt:

    • Navigate to the folder with your files
    • Run this command:
      ollama create krish-mind -f Modelfile
      
  5. Chat with Krish Mind:

    ollama run krish-mind
    

    Now you can type messages and chat! πŸŽ‰


Option 2: Use with LM Studio (Visual App, No Coding!)

LM Studio is a beautiful desktop app for running AI models.

Steps:

  1. Download LM Studio:

  2. Load the Model:

    • In LM Studio, click "My Models" (left sidebar)
    • Click "Import from file"
    • Select the krish-mind-standalone-Q4.gguf file you downloaded
  3. Start Chatting:

    • Click on the model to load it
    • Use the chat interface to talk with Krish Mind!

Option 3: Use with Python (For Developers)

If you know Python, you can use the gguf compatible libraries to load and run the model.

Requirements:

  • Python 3.8 or newer
  • 8+ GB RAM (for Q4) or 32+ GB RAM (for Full)

Installation:

pip install ctransformers

Code Example:

from ctransformers import AutoModelForCausalLM

# Load the model (use the Q4 version for most computers)
model = AutoModelForCausalLM.from_pretrained(
    "Krishkanth/krish-mind",
    model_file="krish-mind-standalone-Q4.gguf",
    model_type="llama"
)

# Chat with the model
response = model("Hello! Who are you?")
print(response)

πŸ’» System Requirements

Minimum (for Q4 version):

  • RAM: 8 GB (16 GB recommended)
  • Storage: 6 GB free space
  • CPU: Any modern processor (Intel i5/AMD Ryzen 5 or better)
  • GPU: Not required! Works on CPU only.

Recommended (for Full version):

  • RAM: 32 GB or more
  • Storage: 20 GB free space
  • CPU: Intel i7/AMD Ryzen 7 or better
  • GPU: Optional but helpful

❓ Frequently Asked Questions

Q: What is GGUF?

A: GGUF is a file format that makes AI models smaller and faster. It allows you to run AI on your own computer without needing expensive cloud services or GPUs.

Q: What's the difference between Q4 and Full version?

A:

  • Q4 = Compressed version, smaller file, uses less RAM, slightly lower quality
  • Full = Original quality, bigger file, needs more RAM, best responses

Q: Can I run this on my phone?

A: Not directly, but there are some Android apps that support GGUF models. Check out "Maid" or "LLM Farm" on the app stores.

Q: Is this free to use?

A: Yes! This model is released under the Apache 2.0 license. You can use it for personal or commercial projects.


πŸ™ Credits

  • Created by: Krish CS
  • Model: Krish Mind - An independent AI assistant

πŸ“ž Need Help?

If you have questions or run into problems:

  1. Check the FAQ above
  2. Open an issue in the "Community" tab above
  3. Make sure you have enough RAM for the model you chose

Happy chatting with Krish Mind! 🧠✨

Downloads last month
85
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Space using Krishkanth/krish-mind-gguf-Q4 1