Instructions to use gnukeith/Ocelot-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 gnukeith/Ocelot-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 gnukeith/Ocelot-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gnukeith/Ocelot-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gnukeith/Ocelot-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gnukeith/Ocelot-GGUF:Q4_K_M

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 gnukeith/Ocelot-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gnukeith/Ocelot-GGUF:Q4_K_M

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 gnukeith/Ocelot-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gnukeith/Ocelot-GGUF:Q4_K_M

Use Docker

docker model run hf.co/gnukeith/Ocelot-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use gnukeith/Ocelot-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gnukeith/Ocelot-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gnukeith/Ocelot-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/gnukeith/Ocelot-GGUF:Q4_K_M

Ollama
How to use gnukeith/Ocelot-GGUF with Ollama:
```
ollama run hf.co/gnukeith/Ocelot-GGUF:Q4_K_M
```

Unsloth Studio

How to use gnukeith/Ocelot-GGUF 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 gnukeith/Ocelot-GGUF 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 gnukeith/Ocelot-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gnukeith/Ocelot-GGUF to start chatting

How to use gnukeith/Ocelot-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gnukeith/Ocelot-GGUF:Q4_K_M

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": "gnukeith/Ocelot-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use gnukeith/Ocelot-GGUF with Docker Model Runner:
```
docker model run hf.co/gnukeith/Ocelot-GGUF:Q4_K_M
```

Lemonade

How to use gnukeith/Ocelot-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gnukeith/Ocelot-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ocelot-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use gnukeith/Ocelot-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 gnukeith/Ocelot-GGUF:Q4_K_M

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 gnukeith/Ocelot-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gnukeith/Ocelot-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gnukeith/Ocelot-GGUF:Q4_K_M

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 "gnukeith/Ocelot-GGUF:Q4_K_M" \
  --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"

Ocelot-GGUF / README.md

gnukeith

Upload folder using huggingface_hub

37ebf62 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.81 kB

	---
	license: apache-2.0
	base_model:
	- bravesoftware/Ocelot-1-VL
	- Qwen/Qwen3-VL-4B-Instruct
	pipeline_tag: image-text-to-text
	tags: [gguf, llama.cpp, qwen3-vl, vision, summarization]
	---

	# Ocelot-1-VL GGUF

	Merged and quantized GGUF builds of [bravesoftware/Ocelot-1-VL](https://huggingface.co/bravesoftware/Ocelot-1-VL), a Qwen3-VL-4B LoRA specialized for webpage summarization from page text or screenshots.

	The Ocelot LoRA was merged into `Qwen/Qwen3-VL-4B-Instruct` in BF16 before conversion. The vision projector is separate and is unchanged by the language-side LoRA.

	## Intended use

	This is not a general-purpose assistant. Use it only to summarize webpage text or webpage screenshots with the training-aligned prompt. See the [original model card](https://huggingface.co/bravesoftware/Ocelot-1-VL) for the full prompt contract, limitations, and safety guidance.

	```text
	The is the text of a webpage: <page>
	... page plain text here ...
	</page>
	Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.
	```

	For screenshots, begin with `The following is a screenshot of a webpage:` and append the same fixed instruction.

	## Files

	\| Quant \| Approx. size \| Notes \|
	\|---\|---:\|---\|
	\| `BF16` \| 7.5 GB \| Maximum fidelity \|
	\| `Q8_0` \| 4.0 GB \| Near-BF16 quality \|
	\| `Q6_K` \| 3.1 GB \| High quality \|
	\| `Q5_K_M` / `Q5_K_S` \| 2.7 / 2.6 GB \| 5-bit variants \|
	\| `Q4_K_M` / `Q4_K_S` \| 2.3 / 2.2 GB \| Recommended balance / smaller \|
	\| `Q4_1` / `Q4_0` \| 2.4 / 2.2 GB \| Legacy compatibility \|
	\| `IQ4_NL` / `IQ4_XS` \| 2.2 / 2.1 GB \| Non-linear 4-bit variants \|
	\| `Q3_K_L` / `Q3_K_M` / `Q3_K_S` \| 2.1 / 1.9 / 1.8 GB \| 3-bit variants \|
	\| `Q2_K` \| 1.6 GB \| Maximum compression, largest quality loss \|
	\| `mmproj-Q8_0` / `mmproj-BF16` \| 433 / 813 MB \| Vision projectors \|

	## Run

	```bash
	llama-cli \
	-m Ocelot-1-VL-Q4_K_M.gguf \
	-p 'The is the text of a webpage: <page>Page text here</page> Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.' \
	-n 512 -c 8192
	```

	For screenshots, add `--mmproj mmproj-Ocelot-1-VL-Q8_0.gguf --image webpage.png` and use the screenshot prompt described above.

	## Conversion and validation

	- Adapter revision: `fbc473443eec370c3b551363556ab75d2b485db6`
	- Base revision: `ebb281ec70b05090aa6165b016eac8ec08e71b17`
	- llama.cpp revision: `0278d8362d78c5de291bc03b76016f7f74b2ab77`
	- All 15 language files passed generation smoke tests.
	- `Q4_K_M` with the Q8 projector passed screenshot summarization.
	- Apple M4 Pro Q4 benchmark: 313 prompt tokens/s and 26 generation tokens/s with Metal.

	Quantization can reduce output quality, especially at 2 and 3 bits. Validate against your own webpage corpus before production use.