Instructions to use decisionlabs/mobilitydb-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use decisionlabs/mobilitydb-sql 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 decisionlabs/mobilitydb-sql:Q8_0
# Run inference directly in the terminal:
llama cli -hf decisionlabs/mobilitydb-sql:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf decisionlabs/mobilitydb-sql:Q8_0
# Run inference directly in the terminal:
llama cli -hf decisionlabs/mobilitydb-sql:Q8_0

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 decisionlabs/mobilitydb-sql:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf decisionlabs/mobilitydb-sql:Q8_0

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 decisionlabs/mobilitydb-sql:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf decisionlabs/mobilitydb-sql:Q8_0

Use Docker

docker model run hf.co/decisionlabs/mobilitydb-sql:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use decisionlabs/mobilitydb-sql with Ollama:
```
ollama run hf.co/decisionlabs/mobilitydb-sql:Q8_0
```
Unsloth Desktop

How to use decisionlabs/mobilitydb-sql with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf decisionlabs/mobilitydb-sql:Q8_0

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": "decisionlabs/mobilitydb-sql:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use decisionlabs/mobilitydb-sql with Docker Model Runner:
```
docker model run hf.co/decisionlabs/mobilitydb-sql:Q8_0
```

Lemonade

How to use decisionlabs/mobilitydb-sql with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull decisionlabs/mobilitydb-sql:Q8_0

Run and chat with the model

lemonade run user.mobilitydb-sql-Q8_0

List all available models

lemonade list

Hermes Agent

How to use decisionlabs/mobilitydb-sql with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf decisionlabs/mobilitydb-sql:Q8_0

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 decisionlabs/mobilitydb-sql:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use decisionlabs/mobilitydb-sql with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf decisionlabs/mobilitydb-sql:Q8_0

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 "decisionlabs/mobilitydb-sql:Q8_0" \
  --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"

saburq commited on Sep 19

Commit

3b02248

verified ·

1 Parent(s): e51d629

Add model card

Browse files

Files changed (1) hide show

README.md +24 -0

README.md ADDED Viewed

	@@ -0,0 +1,24 @@

+---
+license: apache-2.0
+base_model: Qwen/Qwen3-0.6B
+tags:
+  - gguf
+  - mobilitydb
+  - text-to-sql
+  - qwen3
+---
+# mobilitydb-sql
+Qwen3-0.6B LoRA for **MobilityDB SQL** (workshop AIS). Not the Gazet geocoder.
+- Base: `Qwen/Qwen3-0.6B` (596M)
+- File: `mobilitydb-sql-q8_0.gguf` (Q8, ~610 MB)
+- Run: see [gazet-mobility/QUICKSTART.md](https://github.com/decision-labs/speculative-ideas/blob/main/gazet-mobility/QUICKSTART.md)
+```bash
+huggingface-cli download decisionlabs/mobilitydb-sql mobilitydb-sql-q8_0.gguf \
+  --local-dir gazet-mobility-train/out
+llama-server -m gazet-mobility-train/out/mobilitydb-sql-q8_0.gguf \
+  --host 127.0.0.1 --port 9000 --ctx-size 2048 --reasoning off
+```