Instructions to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="orivus/Orivus-Coder-v1-3B-Instruct-GGUF",
	filename="qwen2.5-coder-3b-instruct.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf orivus/Orivus-Coder-v1-3B-Instruct-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 orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf orivus/Orivus-Coder-v1-3B-Instruct-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 orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "orivus/Orivus-Coder-v1-3B-Instruct-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": "orivus/Orivus-Coder-v1-3B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

Ollama
How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with Ollama:
```
ollama run hf.co/orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use orivus/Orivus-Coder-v1-3B-Instruct-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 orivus/Orivus-Coder-v1-3B-Instruct-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 orivus/Orivus-Coder-v1-3B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for orivus/Orivus-Coder-v1-3B-Instruct-GGUF to start chatting

Pi new

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf orivus/Orivus-Coder-v1-3B-Instruct-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": "orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf orivus/Orivus-Coder-v1-3B-Instruct-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 orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use orivus/Orivus-Coder-v1-3B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull orivus/Orivus-Coder-v1-3B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Orivus-Coder-v1-3B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Orivus-Coder-v1-3B-Instruct GGUF

Orivus-Coder-v1 is a local code-generation model fine-tuned for the Orivus Edge runtime.

It is designed to execute structured software engineering tasks using real repository context, architectural constraints, and deterministic outputs.

Model Details

Base model: Qwen/Qwen2.5-Coder-3B-Instruct
Format: GGUF
Quantization: Q4_K_M
Prompt format: ChatML
Runtime: llama.cpp-compatible environments

Intended Use

This model is optimized for:

code generation
refactoring
implementation of structured tasks
execution of architecture-driven plans
local AI workflows inside Orivus Edge

This model is not intended to:

define architecture
perform risk analysis
decide migration strategy

Those responsibilities belong to Orivus-Architect.

Prompt Format (ChatML)

The model expects strict ChatML formatting:

<|im_start|>system
You are Orivus-Coder, a precise software engineering execution model. Follow the provided plan, respect architectural constraints, do not invent files or dependencies, and return implementation-ready output.<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant

Runtime Configuration (llama.cpp)

{
  "n_ctx": 8192,
  "temperature": 0.2,
  "top_p": 0.95
}

Orivus Edge Integration

Orivus-Coder operates as the execution engine within Orivus Edge.

Flow:

Orivus-Architect analyzes the system (OODA: Observe, Orient, Decide)
A structured handoff is generated
Orivus-Coder executes the implementation

This separation ensures:

deterministic execution
controlled changes
reduced hallucination
architecture consistency

Capabilities

follows structured instructions
respects file boundaries
avoids inventing dependencies
produces implementation-ready output
works with partial context (context-aware)

Limitations

requires correct prompt structure
depends on quality of handoff input
not optimized for open-ended chat
limited reasoning depth compared to larger models

Available Files

qwen2.5-coder-3b-instruct.Q4_K_M.gguf

Notes

This model is fine-tuned for local-first execution and integration into controlled engineering systems. It is designed to operate without cloud dependencies as part of the Orivus Edge runtime.

Downloads last month: 246

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for orivus/Orivus-Coder-v1-3B-Instruct-GGUF

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Quantized

(98)

this model