Instructions to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2")
model = AutoModelForCausalLM.from_pretrained("pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2

SGLang

How to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 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 pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 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 pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2",
    max_seq_length=2048,
)

Docker Model Runner
How to use pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 with Docker Model Runner:
```
docker model run hf.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A Hindi instruction-tuned version of Qwen3-4B, fine-tuned to follow instructions and respond naturally in Hindi. Built for developers, researchers, and builders who need a capable, openly-licensed Hindi language model that runs on modest hardware.

Part of the Hindi LLM Series — a collection focused on bringing strong Indic-language models to local and edge deployment.

💡 Looking to run this locally on CPU? Use the GGUF version (Q4/Q5/Q8) with llama.cpp, Ollama, or LM Studio.

Highlights

Strong Hindi instruction-following — trained on 10K curated Hindi instruction–response pairs
Bilingual — handles both Hindi (Devanagari) and English
Compact — 4B parameters, runs comfortably on a single consumer GPU; quantizes well for CPU
Open license — Apache 2.0, commercial use allowed

Example

Prompt:

भारत की राजधानी क्या है? एक वाक्य में उत्तर दें।

Response:

<!-- PASTE A REAL OUTPUT FROM YOUR TEST HERE -->

(Replace the block above with an actual response from your testing — authentic examples build far more trust than invented ones.)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "मुझे स्वस्थ रहने के तीन आसान तरीके बताओ।"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Model Details

Property	Value
Base model	Qwen/Qwen3-4B-Instruct-2507
Parameters	~4B
Fine-tuning method	LoRA (r=32, α=32) via Unsloth
Training data	10K Hindi instruction–response pairs
Languages	Hindi (hi), English (en)
Context length	inherited from base
License	Apache 2.0

Training

Fine-tuned with Unsloth for efficient LoRA training. The dataset was filtered to keep only genuinely Hindi (Devanagari) responses, then formatted with the Qwen chat template and trained for one full epoch. The resulting LoRA was merged into 16-bit weights and exported.

Intended Use & Limitations

Intended for: Hindi chat and assistant applications, instruction-following, Indic-language experimentation, and local/edge deployment via GGUF.

Limitations: As a 4B model, it can make factual errors and may produce inconsistent results on complex reasoning or specialized domains. It inherits any biases present in the base model and training data. Validate outputs before production use.