Instructions to use katanemo/Arch-Router-1.5B.gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use katanemo/Arch-Router-1.5B.gguf with Transformers:

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

pipe = pipeline("text-generation", model="katanemo/Arch-Router-1.5B.gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("katanemo/Arch-Router-1.5B.gguf", dtype="auto")

llama-cpp-python

How to use katanemo/Arch-Router-1.5B.gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="katanemo/Arch-Router-1.5B.gguf",
	filename="Arch-Router-1.5B-Q2_K.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 katanemo/Arch-Router-1.5B.gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf katanemo/Arch-Router-1.5B.gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf katanemo/Arch-Router-1.5B.gguf:Q4_K_M

Use Docker

docker model run hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use katanemo/Arch-Router-1.5B.gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "katanemo/Arch-Router-1.5B.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": "katanemo/Arch-Router-1.5B.gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M

SGLang

How to use katanemo/Arch-Router-1.5B.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 "katanemo/Arch-Router-1.5B.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": "katanemo/Arch-Router-1.5B.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 "katanemo/Arch-Router-1.5B.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": "katanemo/Arch-Router-1.5B.gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use katanemo/Arch-Router-1.5B.gguf with Ollama:
```
ollama run hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
```

Unsloth Studio new

How to use katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for katanemo/Arch-Router-1.5B.gguf to start chatting

Pi new

How to use katanemo/Arch-Router-1.5B.gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf katanemo/Arch-Router-1.5B.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": "katanemo/Arch-Router-1.5B.gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.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 katanemo/Arch-Router-1.5B.gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use katanemo/Arch-Router-1.5B.gguf with Docker Model Runner:
```
docker model run hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
```

Lemonade

How to use katanemo/Arch-Router-1.5B.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull katanemo/Arch-Router-1.5B.gguf:Q4_K_M

Run and chat with the model

lemonade run user.Arch-Router-1.5B.gguf-Q4_K_M

List all available models

lemonade list

Add links to paper page, Github repository and project page

by nielsr HF Staff - opened Jun 28, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+11

-8

Files changed (1) hide show

README.md +11 -8

README.md CHANGED Viewed

@@ -1,14 +1,13 @@
 ---
-license: other
-license_name: katanemo-research
-license_link: >-
-  https://huggingface.co/katanemo/Arch-Router-1.5B.gguf/blob/main/LICENSE
 base_model:
 - Qwen/Qwen2.5-1.5B-Instruct
 language:
 - en
-pipeline_tag: text-generation
 library_name: transformers
 ---
 # katanemo/Arch-Router-1.5B
@@ -19,7 +18,7 @@ With the rapid proliferation of large language models (LLMs) -- each optimized f
 We introduce a preference-aligned routing framework that guides model selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) -- offering a practical mechanism to encode preferences in routing decisions. Specifically, we introduce Arch-Router, a compact 1.5B model that learns to map queries to domain-action preferences for model routing decisions. Experiments on conversational datasets demonstrate that our approach achieves state-of-the-art (SOTA) results in matching queries with human preferences, outperforming top proprietary models.
-This model is described in the paper: https://arxiv.org/abs/2506.16655, and powers [Arch](https://github.com/katanemo/arch) the open-source AI-native proxy for agents to enable preference-based routing in a seamless way.
 ### How It Works
@@ -62,11 +61,15 @@ TASK_INSTRUCTION = """
 You are a helpful assistant designed to find the best suited route.
 You are provided with route description within <routes></routes> XML tags:
 <routes>
-\n{routes}\n
 </routes>
 <conversation>
-\n{conversation}\n
 </conversation>
 """

 ---
 base_model:
 - Qwen/Qwen2.5-1.5B-Instruct
 language:
 - en
 library_name: transformers
+license: other
+license_name: katanemo-research
+license_link: https://huggingface.co/katanemo/Arch-Router-1.5B.gguf/blob/main/LICENSE
+pipeline_tag: text-generation
 ---
 # katanemo/Arch-Router-1.5B
 We introduce a preference-aligned routing framework that guides model selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) -- offering a practical mechanism to encode preferences in routing decisions. Specifically, we introduce Arch-Router, a compact 1.5B model that learns to map queries to domain-action preferences for model routing decisions. Experiments on conversational datasets demonstrate that our approach achieves state-of-the-art (SOTA) results in matching queries with human preferences, outperforming top proprietary models.
+This model is described in the paper: https://arxiv.org/abs/2506.16655, and powers [Arch](https://github.com/katanemo/arch) the open-source AI-native proxy for agents to enable preference-based routing in a seamless way. The project page can be found at https://archgw.com/.
 ### How It Works
 You are a helpful assistant designed to find the best suited route.
 You are provided with route description within <routes></routes> XML tags:
 <routes>
+{routes}
 </routes>
 <conversation>
+{conversation}
 </conversation>
 """