Instructions to use the-acai/iki-gemma-cleanup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use the-acai/iki-gemma-cleanup 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 the-acai/iki-gemma-cleanup:Q4_0
# Run inference directly in the terminal:
llama cli -hf the-acai/iki-gemma-cleanup:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf the-acai/iki-gemma-cleanup:Q4_0
# Run inference directly in the terminal:
llama cli -hf the-acai/iki-gemma-cleanup:Q4_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 the-acai/iki-gemma-cleanup:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf the-acai/iki-gemma-cleanup:Q4_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 the-acai/iki-gemma-cleanup:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf the-acai/iki-gemma-cleanup:Q4_0

Use Docker

docker model run hf.co/the-acai/iki-gemma-cleanup:Q4_0

LM Studio
Jan
Ollama
How to use the-acai/iki-gemma-cleanup with Ollama:
```
ollama run hf.co/the-acai/iki-gemma-cleanup:Q4_0
```
Unsloth Desktop

How to use the-acai/iki-gemma-cleanup with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf the-acai/iki-gemma-cleanup:Q4_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": "the-acai/iki-gemma-cleanup:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use the-acai/iki-gemma-cleanup with Docker Model Runner:
```
docker model run hf.co/the-acai/iki-gemma-cleanup:Q4_0
```

Lemonade

How to use the-acai/iki-gemma-cleanup with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull the-acai/iki-gemma-cleanup:Q4_0

Run and chat with the model

lemonade run user.iki-gemma-cleanup-Q4_0

List all available models

lemonade list

Hermes Agent

How to use the-acai/iki-gemma-cleanup with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf the-acai/iki-gemma-cleanup:Q4_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 the-acai/iki-gemma-cleanup:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use the-acai/iki-gemma-cleanup with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf the-acai/iki-gemma-cleanup:Q4_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 "the-acai/iki-gemma-cleanup:Q4_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"

Iki cleanup model — Gemma 4 E2B "iki6" (Q4_0)

Fine-tuned cleanup model for Iki, the on-device macOS dictation app. QLoRA r32/α32, 3 epochs, merged into google/gemma-4-E2B-it and quantized to Q4_0 with llama.cpp.

Training data is synthetic/public only — no user dictation, no PHI: in-repo synthetic clinical/social-work lines, templated numeral-convention lines, the Iki benchmark references, and a wikitext-103 sample (CC BY-SA), corrupted with Iki's generator (iki-bench generate-cleanup-dataset, dataset v6, 9,151 rows). See docs/MODEL_PROVENANCE.md in the Iki repo.

Gates vs stock E2B Q4_0 (Iki's harness): cleanup-corpus exact match 54.7% → 73.6%, numeral golden 18/31 → 28/31, profanity preservation 20/20, hand check 50/50 with zero invented content, WER within noise, p95 cleanup latency 1531 → 509 ms.

The Iki app downloads gemma-4-E2B-it-iki6-Q4_0.gguf from this repo on first launch.

Downloads last month: 27

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for the-acai/iki-gemma-cleanup

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(330)

this model