Instructions to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vikasit-ai/Vikasit-AI-Vikasit-3-Flash",
	filename="vikasit-3-flash-final.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash
# Run inference directly in the terminal:
llama-cli -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash
# Run inference directly in the terminal:
llama-cli -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash

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 vikasit-ai/Vikasit-AI-Vikasit-3-Flash
# Run inference directly in the terminal:
./llama-cli -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash

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 vikasit-ai/Vikasit-AI-Vikasit-3-Flash
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vikasit-ai/Vikasit-AI-Vikasit-3-Flash

Use Docker

docker model run hf.co/vikasit-ai/Vikasit-AI-Vikasit-3-Flash

LM Studio
Jan
Ollama
How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with Ollama:
```
ollama run hf.co/vikasit-ai/Vikasit-AI-Vikasit-3-Flash
```

Unsloth Studio

How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash 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 vikasit-ai/Vikasit-AI-Vikasit-3-Flash 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 vikasit-ai/Vikasit-AI-Vikasit-3-Flash to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vikasit-ai/Vikasit-AI-Vikasit-3-Flash to start chatting

Docker Model Runner
How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with Docker Model Runner:
```
docker model run hf.co/vikasit-ai/Vikasit-AI-Vikasit-3-Flash
```

Lemonade

How to use vikasit-ai/Vikasit-AI-Vikasit-3-Flash with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vikasit-ai/Vikasit-AI-Vikasit-3-Flash

Run and chat with the model

lemonade run user.Vikasit-AI-Vikasit-3-Flash-{{QUANT_TAG}}

List all available models

lemonade list

Vikasit 3 Flash

By Chandorkar Technologies

High-performance AI model optimized for the Indian ecosystem.

Base: Qwen/Qwen3.5-9B
Quantization: Q4_K_M
Format: GGUF

Usage

ollama run vikasit-ai/3-flash

Built by Chandorkar Technologies.

Downloads last month: 2

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for vikasit-ai/Vikasit-AI-Vikasit-3-Flash

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(259)

this model