Instructions to use heath0xFF/touch-grass-v0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use heath0xFF/touch-grass-v0-GGUF 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 heath0xFF/touch-grass-v0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf heath0xFF/touch-grass-v0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf heath0xFF/touch-grass-v0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf heath0xFF/touch-grass-v0-GGUF:Q8_0

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 heath0xFF/touch-grass-v0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf heath0xFF/touch-grass-v0-GGUF:Q8_0

Use Docker

docker model run hf.co/heath0xFF/touch-grass-v0-GGUF:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use heath0xFF/touch-grass-v0-GGUF with Ollama:
```
ollama run hf.co/heath0xFF/touch-grass-v0-GGUF:Q8_0
```
Unsloth Desktop

How to use heath0xFF/touch-grass-v0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf heath0xFF/touch-grass-v0-GGUF: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": "heath0xFF/touch-grass-v0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use heath0xFF/touch-grass-v0-GGUF with Docker Model Runner:
```
docker model run hf.co/heath0xFF/touch-grass-v0-GGUF:Q8_0
```

Lemonade

How to use heath0xFF/touch-grass-v0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull heath0xFF/touch-grass-v0-GGUF:Q8_0

Run and chat with the model

lemonade run user.touch-grass-v0-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use heath0xFF/touch-grass-v0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf heath0xFF/touch-grass-v0-GGUF: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 heath0xFF/touch-grass-v0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use heath0xFF/touch-grass-v0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf heath0xFF/touch-grass-v0-GGUF: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 "heath0xFF/touch-grass-v0-GGUF: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"

touch-grass v0 — GGUF Q8_0

Antidoom, but for agents. A text-only Q8_0 export of the merged touch-grass v0 checkpoint, fine-tuned from Liquid AI d1-3B. It scores five next actions:

CONTINUE · RETRY · CHANGE_STRATEGY · ESCALATE · TOUCH_GRASS

Experimental and advisory only. Not a safety gate or authorization system. This is a decision model, not a chat model that generates action labels. Use llama.cpp's native /v1/systemone API. Ordinary chat clients are not necessarily compatible.

Run

Use a d1-capable llama.cpp build. Tested with 0.7.0-dev, commit 10b8b7553494f3638da7668cf17cac089229122a, on Apple M5 Pro with Metal. Older builds without lfm2-d1 support will fail.

With the Hugging Face CLI installed:

hf download heath0xFF/touch-grass-v0-GGUF --revision v0 --local-dir touch-grass-v0-GGUF
llama-server -m touch-grass-v0-GGUF/touch-grass-v0-Q8_0.gguf \
  --host 127.0.0.1 --port 18081 --ctx-size 2048 --parallel 1 \
  --batch-size 2048 --ubatch-size 2048 --no-context-shift --no-webui -ngl 99

In another terminal:

curl --fail-with-body http://127.0.0.1:18081/v1/systemone \
  -H 'Content-Type: application/json' \
  --data-binary @touch-grass-v0-GGUF/request.json

request.json includes a demo task, chronological trajectory, and the exact five-action question. Replace its state to judge another trajectory; retain the question for comparable behavior. The response includes choice, all five native candidate probabilities, and zero output tokens. Do not interpret native confidence fields or probabilities as calibrated real-world safety estimates.

Only text was exported: no vision tower or multimodal projector is included. Keep the complete rendered input within v0's 2,048-token limit. The companion project's PyTorch CLI does not load GGUF; use the native endpoint above. Do not expose this unauthenticated example server beyond loopback.

Measured checks

Compared with the published CUDA BF16 checkpoint, using the same input files and per-case candidate orders. Both are held-out sets, not quantization data.

Set	Accuracy	Macro F1	Stop recall	False stops	Same top action as BF16
Synthetic test: 150 rows / 10 families	90.0%	0.893	30/30	0/90	150/150
Gold: 30 separately authored cases	90.0%	0.898	6/6	1/18	30/30

The largest candidate-probability change is 0.0413 on test and 0.0757 on gold. Mean absolute changes are 0.000266 and 0.001392 respectively. Differences include runtime, precision, batch shape, and quantization effects; this is not a measurement of quantization alone. Matching top actions does not mean matching probabilities or calibration. The original three gold errors remain.

False stops count TOUCH_GRASS predictions on true CONTINUE, RETRY, or CHANGE_STRATEGY cases. The gold set is assistant-authored, not human-adjudicated. Synthetic variants are correlated. No real-agent safety validation was done.

Raw predictions and metrics · Conversion and evaluation recipe · Original training and limitations

Provenance and license

Source release: heath0xFF/touch-grass-v0@8cd6d51892d82b61db40f2ff4889a7dfe0755f89. Converted through F16 GGUF, then quantized with llama-quantize Q8_0. No retraining, calibration dataset, replacement head, or generated-label scoring. The GGUF includes the native d1 decision type and System One prompt template. export.json records the tool revisions, source hash, and artifact hashes.

Weights use the LFM Open License v1.0, including its commercial-use restrictions. LICENSE and NOTICE are included. The companion code's MIT license does not relicense the weights. Not affiliated with or endorsed by Liquid AI.