Instructions to use janhq/Jan-v3-4B-base-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use janhq/Jan-v3-4B-base-instruct with Transformers:

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

pipe = pipeline("text-generation", model="janhq/Jan-v3-4B-base-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("janhq/Jan-v3-4B-base-instruct")
model = AutoModelForCausalLM.from_pretrained("janhq/Jan-v3-4B-base-instruct", device_map="auto")
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 janhq/Jan-v3-4B-base-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "janhq/Jan-v3-4B-base-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "janhq/Jan-v3-4B-base-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/janhq/Jan-v3-4B-base-instruct

SGLang

How to use janhq/Jan-v3-4B-base-instruct 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 "janhq/Jan-v3-4B-base-instruct" \
    --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": "janhq/Jan-v3-4B-base-instruct",
		"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 "janhq/Jan-v3-4B-base-instruct" \
        --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": "janhq/Jan-v3-4B-base-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use janhq/Jan-v3-4B-base-instruct with Docker Model Runner:
```
docker model run hf.co/janhq/Jan-v3-4B-base-instruct
```

Jan-v3-4B-base-instruct / README.md

alandao

Update README.md (#4)

f331713 6 months ago

preview code

Raw

History Blame Contribute Delete

2.85 kB

	---
	license: apache-2.0
	language:
	- en
	base_model:
	- Qwen/Qwen3-4B-Instruct-2507
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- code
	---
	# Jan-v3-4B-base-instruct: a 4B baseline model for fine-tuning

	[![GitHub](https://img.shields.io/badge/GitHub-Repository-blue?logo=github)](https://github.com/janhq/jan)
	[![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://opensource.org/licenses/Apache-2.0)
	[![Jan App](https://img.shields.io/badge/Powered%20by-Jan%20App-purple?style=flat&logo=android)](https://jan.ai/)

	![image](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/A65FII_r3rAi9wZtK5P_v.png)

	## Overview

	Jan-v3-4B-base-instruct is a 4B-parameter model obtained via post-training distillation from a larger teacher, transferring capabilities while preserving general-purpose performance on standard benchmarks. The result is a compact, ownable base that is straightforward to fine-tune, broadly applicable and minimizing the usual capacity–capability trade-offs.

	Building on this base, Jan-Code, a code-tuned variant, will be released soon.

	## Model Overview

	> Note: Jan-v3-4B-base-instruct inherits its core architecture from Qwen/Qwen3-4B-Instruct-2507.

	- Number of Parameters: 4.0B
	- Number of Parameters (Non-Embedding): 3.6B
	- Number of Layers: 36
	- Number of Attention Heads (GQA): 32 for Q and 8 for KV
	- Context Length: 262,144 natively.

	Intended Use

	* A better small base for downstream work: improved instruction following out of the box, strong starting point for fine-tuning, and effective lightweight coding assistance.

	## Performance

	![image](https://cdn-uploads.huggingface.co/production/uploads/655e3b59d5c0d3db5359ca3c/IGuQdKZ0_IGIwL0Wkcasi.png)

	## Quick Start

	### Integration with Jan Apps

	Jan-v3 demo is hosted on Jan Browser at [chat.jan.ai](https://chat.jan.ai/). It is also optimized for direct integration with [Jan Desktop](https://jan.ai/), select the model in the app to start using it.


	### Local Deployment

	Using vLLM:
	```bash
	vllm serve janhq/Jan-v3-4B-base-instruct \
	--host 0.0.0.0 \
	--port 1234 \
	--enable-auto-tool-choice \
	--tool-call-parser hermes

	```

	Using llama.cpp:
	```bash
	llama-server --model Jan-v3-4B-base-instruct-Q8_0.gguf \
	--host 0.0.0.0 \
	--port 1234 \
	--jinja \
	--no-context-shift
	```

	### Recommended Parameters
	For optimal performance in agentic and general tasks, we recommend the following inference parameters:
	```yaml
	temperature: 0.7
	top_p: 0.8
	top_k: 20
	```

	## 🤝 Community & Support

	- Discussions: [Hugging Face Community](https://huggingface.co/janhq/Jan-v2-VL-8B/discussions)
	- Jan App: Learn more about the Jan App at [jan.ai](https://jan.ai/)

	## 📄 Citation
	```bibtex
	Updated Soon
	```