Instructions to use affableiq/dax1-routed-delivery-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use affableiq/dax1-routed-delivery-v1 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf affableiq/dax1-routed-delivery-v1
# Run inference directly in the terminal:
llama cli -hf affableiq/dax1-routed-delivery-v1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf affableiq/dax1-routed-delivery-v1
# Run inference directly in the terminal:
llama cli -hf affableiq/dax1-routed-delivery-v1

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 affableiq/dax1-routed-delivery-v1
# Run inference directly in the terminal:
./llama-cli -hf affableiq/dax1-routed-delivery-v1

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 affableiq/dax1-routed-delivery-v1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf affableiq/dax1-routed-delivery-v1

Use Docker

docker model run hf.co/affableiq/dax1-routed-delivery-v1

LM Studio
Jan
Ollama
How to use affableiq/dax1-routed-delivery-v1 with Ollama:
```
ollama run hf.co/affableiq/dax1-routed-delivery-v1
```
Unsloth Desktop

How to use affableiq/dax1-routed-delivery-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf affableiq/dax1-routed-delivery-v1

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "affableiq/dax1-routed-delivery-v1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use affableiq/dax1-routed-delivery-v1 with Docker Model Runner:
```
docker model run hf.co/affableiq/dax1-routed-delivery-v1
```

Lemonade

How to use affableiq/dax1-routed-delivery-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull affableiq/dax1-routed-delivery-v1

Run and chat with the model

lemonade run user.dax1-routed-delivery-v1-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use affableiq/dax1-routed-delivery-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf affableiq/dax1-routed-delivery-v1

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 affableiq/dax1-routed-delivery-v1

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use affableiq/dax1-routed-delivery-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf affableiq/dax1-routed-delivery-v1

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "affableiq/dax1-routed-delivery-v1" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

DAX-1 Delivery

This private repository contains two distinct test packages. Do not combine their scores.

`dax1-final.gguf`

One-file IQ3_S GGUF
6,788,274,816 bytes
SHA-256: 6cbb881a03aae833bd1e044b4cfc5d450376ab734f6c594361ee9a1a39d0a9c5
Lineage: converted and quantized directly from /home/ec2-user/dax1-final-merged
That merged HF source scored 305/350 with the router disabled
The exact GGUF scored 293/350 with the router disabled, 350/350 valid JSON, and zero request errors

Router-free GGUF family scores:

Family	Score
Aggregation	22/50
Date/filter/sort	40/50
Duplicate removal	45/50
Formatting cleanup	50/50
Formula repair	50/50
Lookup/join	39/50
Row deletion	47/50

The 305/350 score belongs only to the merged HF source model. Quantization reduced the exact GGUF result by 12 tasks.

`routed-gguf/`

The routed comparison package contains an IQ3_S GGUF, a GGUF LoRA, and the deterministic router. Its corrected measured package result is 329/350.

The historical 337/350 result belongs to an NF4/HF plus LoRA plus router runtime. It is not a GGUF score.

Downloads last month: 20

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support