Instructions to use ricalanis/scrubdata-qwen3-4b-v4-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ricalanis/scrubdata-qwen3-4b-v4-q8",
	filename="Qwen3-4B-Instruct-2507.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 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 ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
# Run inference directly in the terminal:
llama cli -hf ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
# Run inference directly in the terminal:
llama cli -hf ricalanis/scrubdata-qwen3-4b-v4-q8: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 ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ricalanis/scrubdata-qwen3-4b-v4-q8: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 ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

Use Docker

docker model run hf.co/ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

LM Studio
Jan
Ollama
How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with Ollama:
```
ollama run hf.co/ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
```

Unsloth Studio

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 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 ricalanis/scrubdata-qwen3-4b-v4-q8 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 ricalanis/scrubdata-qwen3-4b-v4-q8 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ricalanis/scrubdata-qwen3-4b-v4-q8 to start chatting

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

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": "ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ricalanis/scrubdata-qwen3-4b-v4-q8: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 ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ricalanis/scrubdata-qwen3-4b-v4-q8: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 "ricalanis/scrubdata-qwen3-4b-v4-q8: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"

Docker Model Runner
How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with Docker Model Runner:
```
docker model run hf.co/ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0
```

Lemonade

How to use ricalanis/scrubdata-qwen3-4b-v4-q8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ricalanis/scrubdata-qwen3-4b-v4-q8:Q8_0

Run and chat with the model

lemonade run user.scrubdata-qwen3-4b-v4-q8-Q8_0

List all available models

lemonade list

ScrubData planner — Qwen3-4B fine-tuned for tabular cleaning plans

A ≤4B planner for hands-off data cleaning: it reads an aggregated column profile (per-value frequency counts) and emits a structured JSON cleaning plan that a deterministic pandas executor applies. Built for the Build Small Hackathon (🏡 Backyard AI · Tiny Titan · Well-Tuned).

Live demo: https://huggingface.co/spaces/build-small-hackathon/scrubdata · Code/paper: see the Space repo (docs/paper/) · Traces: build-small-hackathon/scrubdata-traces

What's special about the training data

Every training example is execution-verified: a candidate (dirty table, plan) pair is kept only if running the executor on it provably recovers the known-clean table. Mix: synthetic high-cardinality categorical tables (Zipf long-tail + realistic typos) + 20% real-derived pairs from the Raha benchmarks (cell-aligned, learnable canonicalizations only).

Measured

Canonicalization micro-F1 0.90 (vs 0.45 for a much larger zero-shot generic model, 0.13 for a rule heuristic) on frozen held-out gold.
Real hospital typos (Raha, OOD): repair recall 0.00 → 0.42 from adding the real-derived 20% (synthetic-only fails to transfer — documented honestly).
In production the model is wrapped with reference grounding + calibrated abstention (it never free-generates a canonical for a grounded column type).

How to run

Ollama / llama.cpp (recommended): use the non-thinking Modelfile from the Space repo (notebooks/Modelfile). Q8_0 GGUF: ricalanis/scrubdata-qwen3-4b-v4-q8 (Q4_K_M corrupts this model on Unsloth 2026.6.x exports — use Q8_0).

Transformers (bf16 + adapter): suppress the tool-call tokens at decode time or the base model's tool-calling prior dominates:

model.generate(..., suppress_tokens=[151657, 151658])  # <tool_call>, </tool_call>

Limitations

English-centric; plans use a closed op vocabulary; canonicalization quality on entity columns depends on the reference taxonomy's coverage; not a de-identification guarantee.

Downloads last month: 92

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for ricalanis/scrubdata-qwen3-4b-v4-q8

Base model

Qwen/Qwen3-4B-Instruct-2507

Quantized

(264)

this model