Instructions to use xxrickyxx/Ailo152m-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xxrickyxx/Ailo152m-v3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xxrickyxx/Ailo152m-v3",
	filename="ailo-152m-v3-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xxrickyxx/Ailo152m-v3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xxrickyxx/Ailo152m-v3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf xxrickyxx/Ailo152m-v3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xxrickyxx/Ailo152m-v3:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf xxrickyxx/Ailo152m-v3: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 xxrickyxx/Ailo152m-v3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf xxrickyxx/Ailo152m-v3: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 xxrickyxx/Ailo152m-v3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xxrickyxx/Ailo152m-v3:Q4_K_M

Use Docker

docker model run hf.co/xxrickyxx/Ailo152m-v3:Q4_K_M

LM Studio
Jan

vLLM

How to use xxrickyxx/Ailo152m-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xxrickyxx/Ailo152m-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xxrickyxx/Ailo152m-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xxrickyxx/Ailo152m-v3:Q4_K_M

Ollama
How to use xxrickyxx/Ailo152m-v3 with Ollama:
```
ollama run hf.co/xxrickyxx/Ailo152m-v3:Q4_K_M
```

Unsloth Studio

How to use xxrickyxx/Ailo152m-v3 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 xxrickyxx/Ailo152m-v3 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 xxrickyxx/Ailo152m-v3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xxrickyxx/Ailo152m-v3 to start chatting

Docker Model Runner
How to use xxrickyxx/Ailo152m-v3 with Docker Model Runner:
```
docker model run hf.co/xxrickyxx/Ailo152m-v3:Q4_K_M
```

Lemonade

How to use xxrickyxx/Ailo152m-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xxrickyxx/Ailo152m-v3:Q4_K_M

Run and chat with the model

lemonade run user.Ailo152m-v3-Q4_K_M

List all available models

lemonade list

AILO-152M-v3 Tiny LLM improved via true logit distillation ⚡

A 152M-parameter assistant, now with a better base model thanks to true logit-level knowledge distillation from a larger teacher — then instruction‑tuned. GGUF, runs on CPU and edge.

AILO-152M-v3 is the third iteration of AILO (Artificial Intelligence Language Operator). The novelty: instead of learning only from the teacher's text, the base model was trained to match the teacher's full token probability distribution (logit-KD, the classic Hinton KD) — possible because teacher and student share the same GPT-2 tokenizer. The improved base was then re-fine-tuned for chat, reasoning and tool use.

ollama run Alieno/ailo-152m-v3
>>> What is the capital of Italy?
The capital of Italy is Rome.

What's new in v3


🧬 Method	true logit-KD (KL-divergence on token distributions) from GPT-Neo 1.3B (same GPT-2 vocab)
📉 Base LM	wikitext perplexity 126 → 84 (−33%) after distillation
💬 Assistant	chat perplexity −7.3% vs v2 (held-out, masked on responses) — then SFT (instruction + reasoning + tool)
🪶 Size	151.9M params · 97 MB (q4_k_m) – 291 MB (f16) · CPU & edge

Honest note: the teacher (GPT-Neo) is a raw 2020 LM, so logit-KD mainly improves base language modeling; the measured net effect on the final assistant is a real but modest −7.3% chat perplexity vs v2. Stronger teachers (e.g. Gemma) can't be used for logit-KD here because their tokenizers differ from AILO's.

Quick start (Ollama)

ollama run Alieno/ailo-152m-v3

Tags: :latest / :q8_0 (best, 156 MB) · :q4_k_m (smallest, 97 MB) · :f16 (291 MB).

Chat format

<|user|>
{question}
<|assistant|>
<think>{optional reasoning}</think>
{answer}<|end|>

Details

Property	Value
Parameters	151.9M
Architecture	Decoder-only Transformer (LayerNorm · RoPE · SwiGLU), 12L / 768 / 12H, ctx 512
Vocabulary	50,257 (GPT-2 BPE)
Pipeline	base → logit-KD from GPT-Neo 1.3B → SFT (Alpaca + GSM8K + SQuAD + tool-use)
Formats	GGUF (q4_k_m, q8_0, f16) — model only, no loader scripts

Limitations

152M params: limited world knowledge and multi-step reasoning. Best paired with retrieval/tools (the AILO system).
512-token context; short prompts. For exact math, use a calculator tool.
English. The logit-KD gain is bounded by the 152M capacity ceiling.

License & contact

Dual-license: CC BY-NC-SA 4.0 (research/education/personal) + commercial by separate agreement. Riccardo Sparacino — LinkedIn

@misc{ailo152m_v3_2026,
  title  = {AILO-152M-v3: A tiny LLM improved via true logit distillation},
  author = {Sparacino, Riccardo}, year = {2026},
  note   = {Dual-licensed CC BY-NC-SA 4.0 / commercial}
}

Acknowledgments

Teacher for logit-KD: GPT-Neo 1.3B (EleutherAI). Built with Ollama and llama.cpp.

Downloads last month: 24

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

16-bit