Instructions to use nuroai/Avalon-2B-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 nuroai/Avalon-2B-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 nuroai/Avalon-2B-GGUF
# Run inference directly in the terminal:
llama cli -hf nuroai/Avalon-2B-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nuroai/Avalon-2B-GGUF
# Run inference directly in the terminal:
llama cli -hf nuroai/Avalon-2B-GGUF

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 nuroai/Avalon-2B-GGUF
# Run inference directly in the terminal:
./llama-cli -hf nuroai/Avalon-2B-GGUF

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 nuroai/Avalon-2B-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nuroai/Avalon-2B-GGUF

Use Docker

docker model run hf.co/nuroai/Avalon-2B-GGUF

LM Studio
Jan

vLLM

How to use nuroai/Avalon-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nuroai/Avalon-2B-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": "nuroai/Avalon-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nuroai/Avalon-2B-GGUF

Ollama
How to use nuroai/Avalon-2B-GGUF with Ollama:
```
ollama run hf.co/nuroai/Avalon-2B-GGUF
```

Unsloth Studio

How to use nuroai/Avalon-2B-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 nuroai/Avalon-2B-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 nuroai/Avalon-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nuroai/Avalon-2B-GGUF to start chatting

How to use nuroai/Avalon-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nuroai/Avalon-2B-GGUF

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": "nuroai/Avalon-2B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nuroai/Avalon-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/nuroai/Avalon-2B-GGUF
```

Lemonade

How to use nuroai/Avalon-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nuroai/Avalon-2B-GGUF

Run and chat with the model

lemonade run user.Avalon-2B-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use nuroai/Avalon-2B-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 nuroai/Avalon-2B-GGUF

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 nuroai/Avalon-2B-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nuroai/Avalon-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nuroai/Avalon-2B-GGUF

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 "nuroai/Avalon-2B-GGUF" \
  --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"

AVALON-2B GGUF

Quantized for On-Device Deployment

Full Model | Paper | GitHub

Overview

This is the GGUF quantized version of AVALON-2B, the first sub-3B self-reflective language model. Optimized for on-device inference with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

Available Files

Filename	Quantization	Size	Quality	Use Case
`avalon-2b-q4km.gguf`	Q4_K_M	1.5 GB	Best balance	Recommended

Performance Benchmarks

Tested on Apple Silicon with llama.cpp:

Device	Chip	RAM	Speed (tok/s)	Memory
MacBook Air	Apple M3	16 GB	40.2	2.1 GB
MacBook Pro	Apple M3 Pro	18 GB	52.4	2.1 GB
Mac Studio	Apple M2 Ultra	64 GB	78.6	2.0 GB
iPhone 15 Pro	Apple A17 Pro	8 GB	12.4	1.8 GB

Quality Retention

Metric	Full Model	Q4_K_M	Retention
MMLU	62.04%	61.42%	99.0%
Self-RAG Accuracy	82.5%	80.5%	97.6%
Perplexity	Baseline	+1.6%	98.4%

Usage

Ollama (Easiest)

# Create Modelfile
cat > Modelfile << 'EOF'
FROM ./avalon-2b-q4km.gguf

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>
"""

PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7

SYSTEM """You are AVALON, a self-reflective AI assistant. Generate [Retrieval] for time-sensitive questions and [No Retrieval] for factual knowledge. End responses with [Utility:X]."""
EOF

# Create and run
ollama create avalon-2b -f Modelfile
ollama run avalon-2b "What is quantum computing?"

llama.cpp

# Download
wget https://huggingface.co/nuroai/Avalon-2B-GGUF/resolve/main/avalon-2b-q4km.gguf

# Run inference
./llama-cli -m avalon-2b-q4km.gguf \
    -p "<|im_start|>user\nWhat is the capital of France?<|im_end|>\n<|im_start|>assistant\n" \
    -n 128 --temp 0.7

LM Studio

Download avalon-2b-q4km.gguf
Open LM Studio → Local Models → Import
Select the GGUF file
Configure chat template (Qwen/ChatML format)
Start chatting!

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="avalon-2b-q4km.gguf",
    n_ctx=4096,
    n_threads=8,
)

output = llm(
    "<|im_start|>user\nWhat is AI?<|im_end|>\n<|im_start|>assistant\n",
    max_tokens=256,
    temperature=0.7,
    stop=["<|im_end|>"]
)
print(output["choices"][0]["text"])

Self-RAG Tokens

AVALON generates special reflection tokens:

Token	Meaning	When Used
`[Retrieval]`	Needs external info	News, current events, prices
`[No Retrieval]`	Can answer from knowledge	Facts, math, definitions
`[Utility:1-5]`	Response quality rating	End of every response

Example Output:

User: What is the capital of Japan?
Assistant: [No Retrieval]Tokyo is the capital of Japan.[Utility:5]

User: What's the current Bitcoin price?
Assistant: [Retrieval]I need current market data to answer this...[Utility:4]

Hardware Requirements

Platform	Minimum	Recommended
RAM	4 GB	8+ GB
Storage	2 GB	2 GB
GPU	Not required	Metal/CUDA for speed

Authors

Akhil Ponnada - akhil@nuroailabs.com
Naga Sri Arvapalli - nagasri3007@gmail.com

License

Apache 2.0 - Same as the full model.

Citation

@article{ponnada2026avalon,
  title={AVALON-2B: The First Sub-3B Self-Reflective Language Model},
  author={Ponnada, Akhil and Arvapalli, Naga Sri},
  journal={arXiv preprint},
  year={2026}
}

Model tree for nuroai/Avalon-2B-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

nuroai/Avalon-2B

Quantized

(3)

this model

nuroai
/

Avalon-2B-GGUF

AVALON-2B GGUF

Quantized for On-Device Deployment

Overview

Available Files

Performance Benchmarks

Quality Retention

Usage

Ollama (Easiest)

llama.cpp

LM Studio

Python (llama-cpp-python)

Self-RAG Tokens

Hardware Requirements

Authors

License

Citation

Links

Model tree for nuroai/Avalon-2B-GGUF