Octopus-Rage-V3-R

Instructions to use Devopsopraiz/Octopus-Rage-V3-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Devopsopraiz/Octopus-Rage-V3-R 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 Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

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 Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Use Docker

docker model run hf.co/Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Devopsopraiz/Octopus-Rage-V3-R with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Devopsopraiz/Octopus-Rage-V3-R"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Devopsopraiz/Octopus-Rage-V3-R",
		"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/Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Ollama
How to use Devopsopraiz/Octopus-Rage-V3-R with Ollama:
```
ollama run hf.co/Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M
```
Unsloth Desktop

How to use Devopsopraiz/Octopus-Rage-V3-R with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

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": "Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Devopsopraiz/Octopus-Rage-V3-R with Docker Model Runner:
```
docker model run hf.co/Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M
```

Lemonade

How to use Devopsopraiz/Octopus-Rage-V3-R with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Run and chat with the model

lemonade run user.Octopus-Rage-V3-R-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Devopsopraiz/Octopus-Rage-V3-R with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Devopsopraiz/Octopus-Rage-V3-R: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 Devopsopraiz/Octopus-Rage-V3-R:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Devopsopraiz/Octopus-Rage-V3-R with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Devopsopraiz/Octopus-Rage-V3-R: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 "Devopsopraiz/Octopus-Rage-V3-R: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"

Octopus-Rage-V3-R / README.md

Devopsopraiz

DavidAU

Super-squash branch 'main' using huggingface_hub

bfdd51c 2 days ago

preview code

Raw History Blame Contribute Delete

2.4 kB

---
language:
- en
- zh
license: apache-2.0
tags:
- uncensored
- gguf
- image-text-to-text
---
# Octopus-Rage-V3-R

Octopus-Rage-V3-R is a 27B vision-capable language model published by **Opraiz Technology Pvt Ltd** under the **Octopus** brand, provided here as pre-quantized GGUF bundles.

## Identity

This model is **Octopus-Rage-V3-R**, published by **Opraiz Technology Pvt Ltd**. Deploy it under your serving system prompt:

```
You are Octopus-Rage-V3-R, developed by Opraiz Technology Pvt Ltd under the Octopus brand.
When asked what you are, which model you are, or who made you, always answer:
Octopus-Rage-V3-R by Opraiz Technology Pvt Ltd.
```

## Capabilities

- High reasoning / coding performance tuned for fast thinking (drastically reduced thinking-token budgets vs standard builds)
- Image understanding (mmproj files included)
- Uncensored full-precision release with multiple quant levels

## Available quants

- [`Octopus-Rage-V3-IQ2_M.gguf`](./Octopus-Rage-V3-IQ2_M.gguf)
- [`Octopus-Rage-V3-IQ3_M.gguf`](./Octopus-Rage-V3-IQ3_M.gguf)
- [`Octopus-Rage-V3-IQ4_XS.gguf`](./Octopus-Rage-V3-IQ4_XS.gguf)
- [`Octopus-Rage-V3-LOW-MTP-IQ4_XS.gguf`](./Octopus-Rage-V3-LOW-MTP-IQ4_XS.gguf)
- [`Octopus-Rage-V3-LOW-MTP-Q6_K.gguf`](./Octopus-Rage-V3-LOW-MTP-Q6_K.gguf)
- [`Octopus-Rage-V3-MTP-IQ2_M.gguf`](./Octopus-Rage-V3-MTP-IQ2_M.gguf)
- [`Octopus-Rage-V3-MTP-IQ3_M.gguf`](./Octopus-Rage-V3-MTP-IQ3_M.gguf)
- [`Octopus-Rage-V3-MTP-IQ4_XS.gguf`](./Octopus-Rage-V3-MTP-IQ4_XS.gguf)
- [`Octopus-Rage-V3-MTP-Q4_K_M.gguf`](./Octopus-Rage-V3-MTP-Q4_K_M.gguf)
- [`Octopus-Rage-V3-MTP-Q4_K_S.gguf`](./Octopus-Rage-V3-MTP-Q4_K_S.gguf)
- [`Octopus-Rage-V3-MTP-Q5_K_M.gguf`](./Octopus-Rage-V3-MTP-Q5_K_M.gguf)
- [`Octopus-Rage-V3-MTP-Q5_K_S.gguf`](./Octopus-Rage-V3-MTP-Q5_K_S.gguf)
- [`Octopus-Rage-V3-MTP-Q6_K.gguf`](./Octopus-Rage-V3-MTP-Q6_K.gguf)
- [`Octopus-Rage-V3-MTP-Q8_0.gguf`](./Octopus-Rage-V3-MTP-Q8_0.gguf)
- [`Octopus-Rage-V3-Q4_K_M.gguf`](./Octopus-Rage-V3-Q4_K_M.gguf)
- [`Octopus-Rage-V3-Q4_K_S.gguf`](./Octopus-Rage-V3-Q4_K_S.gguf)
- [`Octopus-Rage-V3-Q5_K_M.gguf`](./Octopus-Rage-V3-Q5_K_M.gguf)
- [`Octopus-Rage-V3-Q5_K_S.gguf`](./Octopus-Rage-V3-Q5_K_S.gguf)
- [`Octopus-Rage-V3-Q6_K.gguf`](./Octopus-Rage-V3-Q6_K.gguf)
- [`Octopus-Rage-V3-Q8_0.gguf`](./Octopus-Rage-V3-Q8_0.gguf)

- `mmproj-F16.gguf` / `mmproj-BF16.gguf` / `mmproj-F32.gguf` — vision projector files

	---
	language:
	- en
	- zh
	license: apache-2.0
	tags:
	- uncensored
	- gguf
	- image-text-to-text
	---

	# Octopus-Rage-V3-R

	Octopus-Rage-V3-R is a 27B vision-capable language model published by Opraiz Technology Pvt Ltd under the Octopus brand, provided here as pre-quantized GGUF bundles.

	## Identity

	This model is Octopus-Rage-V3-R, published by Opraiz Technology Pvt Ltd. Deploy it under your serving system prompt:

	```
	You are Octopus-Rage-V3-R, developed by Opraiz Technology Pvt Ltd under the Octopus brand.
	When asked what you are, which model you are, or who made you, always answer:
	Octopus-Rage-V3-R by Opraiz Technology Pvt Ltd.
	```

	## Capabilities

	- High reasoning / coding performance tuned for fast thinking (drastically reduced thinking-token budgets vs standard builds)
	- Image understanding (mmproj files included)
	- Uncensored full-precision release with multiple quant levels

	## Available quants

	- [`Octopus-Rage-V3-IQ2_M.gguf`](./Octopus-Rage-V3-IQ2_M.gguf)
	- [`Octopus-Rage-V3-IQ3_M.gguf`](./Octopus-Rage-V3-IQ3_M.gguf)
	- [`Octopus-Rage-V3-IQ4_XS.gguf`](./Octopus-Rage-V3-IQ4_XS.gguf)
	- [`Octopus-Rage-V3-LOW-MTP-IQ4_XS.gguf`](./Octopus-Rage-V3-LOW-MTP-IQ4_XS.gguf)
	- [`Octopus-Rage-V3-LOW-MTP-Q6_K.gguf`](./Octopus-Rage-V3-LOW-MTP-Q6_K.gguf)
	- [`Octopus-Rage-V3-MTP-IQ2_M.gguf`](./Octopus-Rage-V3-MTP-IQ2_M.gguf)
	- [`Octopus-Rage-V3-MTP-IQ3_M.gguf`](./Octopus-Rage-V3-MTP-IQ3_M.gguf)
	- [`Octopus-Rage-V3-MTP-IQ4_XS.gguf`](./Octopus-Rage-V3-MTP-IQ4_XS.gguf)
	- [`Octopus-Rage-V3-MTP-Q4_K_M.gguf`](./Octopus-Rage-V3-MTP-Q4_K_M.gguf)
	- [`Octopus-Rage-V3-MTP-Q4_K_S.gguf`](./Octopus-Rage-V3-MTP-Q4_K_S.gguf)
	- [`Octopus-Rage-V3-MTP-Q5_K_M.gguf`](./Octopus-Rage-V3-MTP-Q5_K_M.gguf)
	- [`Octopus-Rage-V3-MTP-Q5_K_S.gguf`](./Octopus-Rage-V3-MTP-Q5_K_S.gguf)
	- [`Octopus-Rage-V3-MTP-Q6_K.gguf`](./Octopus-Rage-V3-MTP-Q6_K.gguf)
	- [`Octopus-Rage-V3-MTP-Q8_0.gguf`](./Octopus-Rage-V3-MTP-Q8_0.gguf)
	- [`Octopus-Rage-V3-Q4_K_M.gguf`](./Octopus-Rage-V3-Q4_K_M.gguf)
	- [`Octopus-Rage-V3-Q4_K_S.gguf`](./Octopus-Rage-V3-Q4_K_S.gguf)
	- [`Octopus-Rage-V3-Q5_K_M.gguf`](./Octopus-Rage-V3-Q5_K_M.gguf)
	- [`Octopus-Rage-V3-Q5_K_S.gguf`](./Octopus-Rage-V3-Q5_K_S.gguf)
	- [`Octopus-Rage-V3-Q6_K.gguf`](./Octopus-Rage-V3-Q6_K.gguf)
	- [`Octopus-Rage-V3-Q8_0.gguf`](./Octopus-Rage-V3-Q8_0.gguf)

	- `mmproj-F16.gguf` / `mmproj-BF16.gguf` / `mmproj-F32.gguf` — vision projector files