Instructions to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser 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 Sido/hina-gemma4-e2b-aggressive-iq3m-browser
# Run inference directly in the terminal:
llama cli -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser
# Run inference directly in the terminal:
llama cli -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser
# Run inference directly in the terminal:
./build/bin/llama cli -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Use Docker

docker model run hf.co/Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Llama new
LM Studio
Jan
Ollama
How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with Ollama:
```
ollama run hf.co/Sido/hina-gemma4-e2b-aggressive-iq3m-browser
```
Unsloth Desktop

How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

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": "Sido/hina-gemma4-e2b-aggressive-iq3m-browser"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with Docker Model Runner:
```
docker model run hf.co/Sido/hina-gemma4-e2b-aggressive-iq3m-browser
```

Lemonade

How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Run and chat with the model

lemonade run user.hina-gemma4-e2b-aggressive-iq3m-browser-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

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 Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Sido/hina-gemma4-e2b-aggressive-iq3m-browser with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sido/hina-gemma4-e2b-aggressive-iq3m-browser

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 "Sido/hina-gemma4-e2b-aggressive-iq3m-browser" \
  --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"

Gemma 4 E2B Aggressive IQ3_M — browser shards

This is the text-only IQ3_M GGUF from HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive, revision da8593c3e407afcd3e7da94ff2d69d77e2a28a48, split into files smaller than 2 GB for browser runtimes. No tensor was requantized or otherwise changed. The source file is Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf, 3,134,964,672 bytes, SHA-256 0796d58372742ef8ddc76dd64cd2fde217b7ef32e3dc58e10873253e569cad6b.

The split was made with llama-gguf-split --split-max-size 2000M --no-tensor-first-split. Download the 00001 shard first; GGUF split-aware runtimes find the remaining shards by filename. The upstream repository labels its license gemma; review the upstream model card and applicable terms before use. This mirror does not include the multimodal projector.

Downloads last month: -

GGUF

Model size

5B params

Architecture

gemma4

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

Model tree for Sido/hina-gemma4-e2b-aggressive-iq3m-browser

Base model

HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive

Quantized

(2)

this model