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

Libraries

How to use janhq/Jan-v3-4B-base-instruct-gguf 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-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("janhq/Jan-v3-4B-base-instruct-gguf", dtype="auto")

llama-cpp-python

How to use janhq/Jan-v3-4B-base-instruct-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="janhq/Jan-v3-4B-base-instruct-gguf",
	filename="Jan-v3-4b-base-instruct-Q3_K_L.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use janhq/Jan-v3-4B-base-instruct-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf janhq/Jan-v3-4B-base-instruct-gguf: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 janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf janhq/Jan-v3-4B-base-instruct-gguf: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 janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

Use Docker

docker model run hf.co/janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

LM Studio
Jan

vLLM

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

Use Docker

docker model run hf.co/janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

SGLang

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

Ollama
How to use janhq/Jan-v3-4B-base-instruct-gguf with Ollama:
```
ollama run hf.co/janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
```

Unsloth Studio new

How to use janhq/Jan-v3-4B-base-instruct-gguf 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 janhq/Jan-v3-4B-base-instruct-gguf 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 janhq/Jan-v3-4B-base-instruct-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for janhq/Jan-v3-4B-base-instruct-gguf to start chatting

Pi new

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf janhq/Jan-v3-4B-base-instruct-gguf: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": "janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use janhq/Jan-v3-4B-base-instruct-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf janhq/Jan-v3-4B-base-instruct-gguf: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 janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use janhq/Jan-v3-4B-base-instruct-gguf with Docker Model Runner:
```
docker model run hf.co/janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull janhq/Jan-v3-4B-base-instruct-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Jan-v3-4B-base-instruct-gguf-Q4_K_M

List all available models

lemonade list

Jan-v3-4B-base-instruct: a 4B baseline model for fine-tuning

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

This repo contains the BF16 version of Jan-v3-4B-base-instruct, which has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 4B in total
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

Quick Start

Integration with Jan Apps

Jan-v3 demo is hosted on Jan Browser at chat.jan.ai. It is also 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-v3-4B-base-instruct \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes

Using llama.cpp:

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:

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: 37,827

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for janhq/Jan-v3-4B-base-instruct-gguf

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

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

Quantized

(17)

this model

Collection including janhq/Jan-v3-4B-base-instruct-gguf

Jan-v3

Collection

2 items • Updated Jan 27 • 7