Instructions to use gary23w/gary-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gary23w/gary-5 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gary23w/gary-5",
	filename="gary-5.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gary23w/gary-5 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gary23w/gary-5:Q8_0
# Run inference directly in the terminal:
llama-cli -hf gary23w/gary-5:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gary23w/gary-5:Q8_0
# Run inference directly in the terminal:
llama-cli -hf gary23w/gary-5:Q8_0

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 gary23w/gary-5:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf gary23w/gary-5:Q8_0

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 gary23w/gary-5:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gary23w/gary-5:Q8_0

Use Docker

docker model run hf.co/gary23w/gary-5:Q8_0

LM Studio
Jan

vLLM

How to use gary23w/gary-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gary23w/gary-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gary23w/gary-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gary23w/gary-5:Q8_0

Ollama
How to use gary23w/gary-5 with Ollama:
```
ollama run hf.co/gary23w/gary-5:Q8_0
```

Unsloth Studio

How to use gary23w/gary-5 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 gary23w/gary-5 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 gary23w/gary-5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gary23w/gary-5 to start chatting

Atomic Chat new
Docker Model Runner
How to use gary23w/gary-5 with Docker Model Runner:
```
docker model run hf.co/gary23w/gary-5:Q8_0
```

Lemonade

How to use gary23w/gary-5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gary23w/gary-5:Q8_0

Run and chat with the model

lemonade run user.gary-5-Q8_0

List all available models

lemonade list

gary-5 📱

The pocket-sized chat model that can actually chat. Successor to gary-4 (69 KB of beautiful nonsense). gary-5 trades a few megabytes for the ability to, you know, answer questions.

Built on SmolLM2-135M-Instruct (a distilled instruct model by Hugging Face TB), LoRA fine-tuned for the gary persona, merged, and quantized to GGUF. Runs fully offline on basically anything — phone, Raspberry Pi, that laptop from 2014.

Stats


Parameters	135M
GGUF Q8_0	138 MB
Safetensors (bf16)	260 MB
Base	SmolLM2-135M-Instruct (Apache-2.0)
Fine-tune	LoRA r=16 on all attn+MLP projections, 101 steps, merged
Runs on	CPU, no GPU needed. ~30 tok/s on a sandbox CPU.

Sample (greedy, unedited)

Q: Who are you?
A: I'm gary-5, a pocket-sized AI built by Garrett. Small enough to live on
   your phone, smart enough to be worth talking to.
Q: What is the capital of France?
A: Paris.
Q: Explain what a firewall does in one sentence.
A: A firewall acts like a powerful wall that filters and blocks unauthorized
   traffic before it reaches your device.

Run it

llama.cpp / ollama (recommended, uses the 138 MB GGUF):

llama-cli -m gary-5.Q8_0.gguf -cnv \
  -sys "You are gary-5, a pocket-sized AI assistant created by Garrett."

transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("gary23w/gary-5")
model = AutoModelForCausalLM.from_pretrained("gary23w/gary-5")
msgs = [{"role":"system","content":"You are gary-5, a pocket-sized AI assistant created by Garrett."},
        {"role":"user","content":"hi"}]
enc = tok.apply_chat_template(msgs, add_generation_prompt=True, return_dict=True, return_tensors="pt")
print(tok.decode(model.generate(**enc, max_new_tokens=80)[0], skip_special_tokens=True))

Honest section

It's a 135M model: great at chat, identity, short factual answers, summaries, and one-sentence explanations; it will confidently improvise on hard reasoning and obscure facts. For GPT-4-like performance in your pocket the recipe is this exact pipeline with a 1–3B base — gary-6, presumably.

The gary lineage: gary-4 (67K params, 69 KB, gibberish, beloved) → gary-5 (135M params, 138 MB, coherent) → gary-6 (TBD, pending Garrett's ambitions).

Downloads last month: 25

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for gary23w/gary-5

Base model

HuggingFaceTB/SmolLM2-135M

Quantized

HuggingFaceTB/SmolLM2-135M-Instruct

Adapter

(48)

this model