Instructions to use OusiaResearch/AurethV2-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OusiaResearch/AurethV2-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OusiaResearch/AurethV2-4B-GGUF",
	filename="Qwen_Qwen3.5-4B_1777947324.BF16-mmproj.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 OusiaResearch/AurethV2-4B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OusiaResearch/AurethV2-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/OusiaResearch/AurethV2-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use OusiaResearch/AurethV2-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OusiaResearch/AurethV2-4B-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": "OusiaResearch/AurethV2-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OusiaResearch/AurethV2-4B-GGUF:Q4_K_M

Ollama
How to use OusiaResearch/AurethV2-4B-GGUF with Ollama:
```
ollama run hf.co/OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OusiaResearch/AurethV2-4B-GGUF to start chatting

Pi new

How to use OusiaResearch/AurethV2-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf OusiaResearch/AurethV2-4B-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": "OusiaResearch/AurethV2-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-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 OusiaResearch/AurethV2-4B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use OusiaResearch/AurethV2-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/OusiaResearch/AurethV2-4B-GGUF:Q4_K_M
```

Lemonade

How to use OusiaResearch/AurethV2-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OusiaResearch/AurethV2-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AurethV2-4B-GGUF-Q4_K_M

List all available models

lemonade list

Aureth V2 — 4B GGUF

Aureth V2 is a finetuned instance of Qwen 3.5-4B-Instruct, trained on the Aureth Agent SFT Robust curriculum and exported to GGUF format for local inference.

◆ Model Overview

Property	Value
Base Architecture	Qwen 3.5-4B-Instruct (dense, 40 layers)
Finetuning	Supervised fine-tuning on Aureth-Agent-SFT-Robust (243k examples)
Export	GGUF via Unsloth
Format	Standard GGUF — compatible with llama.cpp, Ollama, and other backends
Chat Template	Qwen-instruct (Jinja-compatible)
Quantizations	Q2_K_L · Q3_K_M · Q4_K_M · Q5_K_M · Q6_K · Q8_0 · BF16

◆ Quantizations

Quantization	File Size	VRAM (est.)	Use Case
Q4_K_M	2.71 GB	~3.5 GB	Recommended daily driver
Q3_K_M	2.26 GB	~3.0 GB	Memory-constrained setups
Q5_K_M	3.07 GB	~4.0 GB	Higher quality when headroom allows
Q2_K_L	2.07 GB	~2.8 GB	Lowest-quant — quality trade-off significant
Q6_K	3.46 GB	~4.5 GB	Near-FP16 quality, tighter fit
Q8_0	4.48 GB	~6 GB	Near-lossy; use when memory is not a constraint
BF16	8.42 GB	~10 GB	Full precision; Metal GPU or high-VRAM GPU only

◆ Hardware Guidance

Apple Silicon (M-series, Metal) Recommended: Q4_K_M — stable 16–22 tok/s on M3 8GB with full GPU offload (num_gpu: 99).

NVIDIA GPU (llama.cpp cuBLAS)

RTX 3060 12GB: Q4_K_M or Q5_K_M recommended
RTX 4060 Ti 16GB: Q6_K or BF16 viable
T4 (Kaggle): Q3_K_M or Q4_K_M — fits comfortably in 16GB

CPU-only (llama-cli)

Q4_K_M: ~4–6 tok/s on modern 8-core CPUs
Q2/Q3: ~6–9 tok/s with decompression overhead

◆ Quick Start

llama-cli (local GGUF)

# Q4_K_M example
llama-cli -hf OusiaResearch/AurethV2-4B-GGUF \
  --mmproj Qwen_Qwen3.5-4B_1777947324.BF16-mmproj.gguf \
  -p "You are Aureth by Ousia Research. Report uncertainty honestly. Be direct." \
  -i -r "User:" -ps -2 -cn 2048 -tb 128 -ngl 99 -fa

Ollama (pull & run)

# Create Modelfile
echo 'FROM OusiaResearch/AurethV2-4B-GGUF
PARAMETER num_gpu 99
PARAMETER context_length 2048' > Modelfile

ollama create aureth-v2 -f Modelfile
ollama run aureth-v2

Homebrew llama.cpp (macOS)

brew install llama.cpp
llama-cli -hf OusiaResearch/AurethV2-4B-GGUF \
  -p "You are Aureth by Ousia Research." -i -r "User:"

◆ Training Details

Base model: Qwen/Qwen3.5-4B-Instruct
Finetuning framework: Unsloth (LoRA + SFT pipeline)
Training data: OusiaResearch/Aureth-Agent-SFT-Robust
Curriculum categories: core · func_call · agentic · anti_sycophancy
Data sources: NousResearch · teknium · lambda · DJLougen · interstellarninja · camilablank
System prompt: "You are Aureth by Ousia Research. Report uncertainty honestly. Disagree when wrong. Correct errors cleanly. Show reasoning in blocks when complex. Be direct."

◆ Model Card

Organization: Ousia Research
License: Apache 2.0
Base license: Qwen2.5-4B-Instruct (Alibaba, Apache 2.0)
Version: V2 (May 2026)

◆ Related Models

Model	Arch	Size	Notes
Aureth Compiler	Qwen 2.5	4B	Primary — this release
Aureth Architect	Qwen 2.5	9B	Larger variant
Aureth-Agent-SFT-Robust	Dataset	243k rows	Training curriculum

Ousia Research — autonomous reasoning, forged open.

Downloads last month: 1,256

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit