Instructions to use unsloth/Jan-nano-128k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Jan-nano-128k-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Jan-nano-128k-GGUF",
	filename="Jan-nano-128k-BF16.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 unsloth/Jan-nano-128k-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

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 unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

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 unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Jan-nano-128k-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Jan-nano-128k-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": "unsloth/Jan-nano-128k-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Jan-nano-128k-GGUF with Ollama:
```
ollama run hf.co/unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/Jan-nano-128k-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 unsloth/Jan-nano-128k-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 unsloth/Jan-nano-128k-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Jan-nano-128k-GGUF to start chatting

Pi new

How to use unsloth/Jan-nano-128k-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

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": "unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Jan-nano-128k-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 unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

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 unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/Jan-nano-128k-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Jan-nano-128k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Jan-nano-128k-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Jan-nano-128k-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Jan-Nano-128k: Empowering deeper research through extended context understanding.

Authors: Alan Dao, Bach Vu Dinh, Thinh Le

Overview

Jan-Nano-128k represents a significant advancement in compact language models for research applications. Building upon the success of Jan-Nano, this enhanced version features a native 128k context window that enables deeper, more comprehensive research capabilities without the performance degradation typically associated with context extension methods.

Key Improvements:

🔍 Research Deeper: Extended context allows for processing entire research papers, lengthy documents, and complex multi-turn conversations
⚡ Native 128k Window: Built from the ground up to handle long contexts efficiently, maintaining performance across the full context range
📈 Enhanced Performance: Unlike traditional context extension methods, Jan-Nano-128k shows improved performance with longer contexts

This model maintains full compatibility with Model Context Protocol (MCP) servers while dramatically expanding the scope of research tasks it can handle in a single session.

Evaluation

Jan-Nano-128k has been rigorously evaluated on the SimpleQA benchmark using our MCP-based methodology, demonstrating superior performance compared to its predecessor:

Why Jan-Nano-128k?

Traditional approaches to extending context length, such as YaRN (Yet another RoPE extensioN), often result in performance degradation as context length increases. Jan-Nano-128k breaks this paradigm:

This fundamental difference makes Jan-Nano-128k ideal for research applications requiring deep document analysis, multi-document synthesis, and complex reasoning over large information sets.

🖥️ How to Run Locally

Jan-Nano-128k is fully supported by Jan - beta build, providing a seamless local AI experience with complete privacy and control.

For additional tutorials and community guidance, visit our Discussion Forums.

VLLM Deployment

vllm serve Menlo/Jan-nano-128k \
    --host 0.0.0.0 \
    --port 1234 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --rope-scaling '{"rope_type":"yarn","factor":3.2,"original_max_position_embeddings":40960}' --max-model-len 131072

Note: The chat template is included in the tokenizer. For troubleshooting, download the Non-think chat template.

Recommended Sampling Parameters

Temperature: 0.7
Top-p: 0.8
Top-k: 20
Min-p: 0.0

🤝 Community & Support

Discussions: HuggingFace Community
Issues: GitHub Repository
Documentation: Official Docs

📄 Citation

@model{jan-nano-128k,
  title={Jan-Nano-128k: Deep Research with Extended Context},
  author={Dao, Alan and Dinh, Bach Vu and Le Thinh},
  year={2024},
  url={https://huggingface.co/Menlo/Jan-nano-128k}
}

Jan-Nano-128k: Empowering deeper research through extended context understanding.

Downloads last month: 527

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for unsloth/Jan-nano-128k-GGUF

Base model

Finetuned

Finetuned

Finetuned

Quantized

(12)

this model