Instructions to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker 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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

Use Docker

docker model run hf.co/jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

LM Studio
Jan
Ollama
How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with Ollama:
```
ollama run hf.co/jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
```

Unsloth Studio

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker 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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker 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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker to start chatting

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

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": "jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

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 "jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL" \
  --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 jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with Docker Model Runner:
```
docker model run hf.co/jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL
```

Lemonade

How to use jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jackasda211233/Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker:IQ4_NL

Run and chat with the model

lemonade run user.Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker-IQ4_NL

List all available models

lemonade list

Gemma-4-E4B-Deckard-AttnQ8-IQ4_NL-storyMaker / docs /deckard_5060ti_probe_20260429_125554_summary.txt

jackasda211233

Add model card and validation docs

90f7365 verified 3 months ago

Raw

History Blame

1.12 kB

	Output: /home/benbi/models/gemma4_deckard_davidau_gguf/evals/deckard_5060ti_probe_20260429_125554
	GPU: GPU-d21e6aeb-f57e-c98c-ad53-f39cb446b4b7

	== llama-bench f16 KV small-context kernel probe ==
	prompt_tok_s=5558.544 kv=f16/f16 prompt=1024 gen=0
	decode_tok_s=105.795 kv=f16/f16 prompt=0 gen=256

	== live-style 120k f32 KV server probe ==
	server_ready=yes
	972609, /home/benbi/llama.cpp/build/bin/llama-server, GPU-d21e6aeb-f57e-c98c-ad53-f39cb446b4b7, 7796
	prompt_n=1352
	prompt_ms=480.019
	prompt_per_second=2816.555178024203
	predicted_n=256
	predicted_ms=3481.02
	predicted_per_second=73.54166307576514

	== server VRAM/KV log lines ==
	load_tensors: offloaded 43/43 layers to GPU
	load_tensors: CUDA0 model buffer size = 2775.92 MiB
	llama_kv_cache_iswa: creating non-SWA KV cache, size = 120064 cells
	llama_kv_cache: CUDA0 KV buffer size = 3752.00 MiB
	llama_kv_cache_iswa: creating SWA KV cache, size = 768 cells
	llama_kv_cache: CUDA0 KV buffer size = 60.00 MiB
	sched_reserve: CUDA0 compute buffer size = 572.00 MiB
	sched_reserve: CUDA_Host compute buffer size = 66.76 MiB

	finished