Instructions to use vipinkp/kambi-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vipinkp/kambi-qwen3-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vipinkp/kambi-qwen3-4b",
	filename="kambi-qwen3-4b.Q4_K_M.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 vipinkp/kambi-qwen3-4b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vipinkp/kambi-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vipinkp/kambi-qwen3-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vipinkp/kambi-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vipinkp/kambi-qwen3-4b: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 vipinkp/kambi-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vipinkp/kambi-qwen3-4b: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 vipinkp/kambi-qwen3-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vipinkp/kambi-qwen3-4b:Q4_K_M

Use Docker

docker model run hf.co/vipinkp/kambi-qwen3-4b:Q4_K_M

LM Studio
Jan
Ollama
How to use vipinkp/kambi-qwen3-4b with Ollama:
```
ollama run hf.co/vipinkp/kambi-qwen3-4b:Q4_K_M
```

Unsloth Studio

How to use vipinkp/kambi-qwen3-4b 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 vipinkp/kambi-qwen3-4b 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 vipinkp/kambi-qwen3-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vipinkp/kambi-qwen3-4b to start chatting

How to use vipinkp/kambi-qwen3-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vipinkp/kambi-qwen3-4b: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": "vipinkp/kambi-qwen3-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vipinkp/kambi-qwen3-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vipinkp/kambi-qwen3-4b: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 vipinkp/kambi-qwen3-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use vipinkp/kambi-qwen3-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vipinkp/kambi-qwen3-4b:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "vipinkp/kambi-qwen3-4b:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use vipinkp/kambi-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/vipinkp/kambi-qwen3-4b:Q4_K_M
```

Lemonade

How to use vipinkp/kambi-qwen3-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vipinkp/kambi-qwen3-4b:Q4_K_M

Run and chat with the model

lemonade run user.kambi-qwen3-4b-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Kambi Qwen3 4B - Malayalam Story Generation Model

Fine-tuned from huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated on Malayalam kambi katha data.

Training Details

Base model: Qwen3 4B Instruct (abliterated)
Dataset: 790 Malayalam kambi stories
Method: QLoRA (rank=16, alpha=16, 4-bit NF4)
Sequence length: 2048 tokens
Epochs: 3
Final eval loss: 0.0210
Hardware: RTX A4500 (20GB) on RunPod

Usage

With Unsloth

from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="vipinkp/kambi-qwen3-4b",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

messages = [{"role": "user", "content": "ഒരു കമ്പി കഥ എഴുതുക."}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=2048, temperature=0.85)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

With llama.cpp (GGUF)

./llama-cli -m kambi-qwen3-4b.Q4_K_M.gguf -p "ഒരു കമ്പി കഥ എഴുതുക." -n 2048 --temp 0.85 -ngl 99

Downloads last month: 14

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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

vipinkp
/

kambi-qwen3-4b

You need to agree to share your contact information to access this model

Kambi Qwen3 4B - Malayalam Story Generation Model

Training Details

Usage

With Unsloth

With llama.cpp (GGUF)

Dataset used to train vipinkp/kambi-qwen3-4b