Instructions to use cyankiwi/Jan-code-4b-AWQ-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/Jan-code-4b-AWQ-8bit with Transformers:

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

pipe = pipeline("text-generation", model="cyankiwi/Jan-code-4b-AWQ-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyankiwi/Jan-code-4b-AWQ-8bit")
model = AutoModelForCausalLM.from_pretrained("cyankiwi/Jan-code-4b-AWQ-8bit")
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

vLLM

How to use cyankiwi/Jan-code-4b-AWQ-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/Jan-code-4b-AWQ-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyankiwi/Jan-code-4b-AWQ-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyankiwi/Jan-code-4b-AWQ-8bit

SGLang

How to use cyankiwi/Jan-code-4b-AWQ-8bit 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 "cyankiwi/Jan-code-4b-AWQ-8bit" \
    --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": "cyankiwi/Jan-code-4b-AWQ-8bit",
		"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 "cyankiwi/Jan-code-4b-AWQ-8bit" \
        --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": "cyankiwi/Jan-code-4b-AWQ-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyankiwi/Jan-code-4b-AWQ-8bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/Jan-code-4b-AWQ-8bit
```

Jan-Code-4B: a small code-tuned model

Overview

Jan-Code-4B is a code-tuned model built on top of Jan-v3-4B-base-instruct. It’s designed to be a practical coding model you can run locally and iterate on quickly—useful for everyday code tasks and as a lightweight “worker” model in agentic workflows.

Compared to larger coding models, Jan-Code focuses on handling well-scoped subtasks reliably while keeping latency and compute requirements small.

Intended Use

Lightweight coding assistant for generation, editing, refactoring, and debugging
A small, fast worker model for agent setups (e.g., as a sub-agent that produces patches/tests while a larger model plans)
Replace Haiku model in Claude Code setup

Quick Start

Integration with Jan Apps

Jan-code is optimized for direct integration with Jan Desktop, select the model in the app to start using it.

Local Deployment

Using vLLM:

vllm serve janhq/Jan-code-4b \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes

Using llama.cpp:

llama-server --model Jan-code-4b-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:

temperature: 0.7
top_p: 0.8
top_k: 20

🤝 Community & Support

Discussions: Hugging Face Community
Jan App: Learn more about the Jan App at jan.ai

📄 Citation

Updated Soon

Downloads last month: 14

Safetensors

Model size

4B params

Tensor type

I64

I32

BF16

Model tree for cyankiwi/Jan-code-4b-AWQ-8bit

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

janhq/Jan-v3-4B-base-instruct

Finetuned

janhq/Jan-code-4b

Quantized

(12)

this model