Instructions to use SmallAICreator/MiniGPT2-22M-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 SmallAICreator/MiniGPT2-22M-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 SmallAICreator/MiniGPT2-22M-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SmallAICreator/MiniGPT2-22M-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

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 SmallAICreator/MiniGPT2-22M-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

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 SmallAICreator/MiniGPT2-22M-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

Use Docker

docker model run hf.co/SmallAICreator/MiniGPT2-22M-GGUF:F16

LM Studio
Jan

vLLM

How to use SmallAICreator/MiniGPT2-22M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SmallAICreator/MiniGPT2-22M-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": "SmallAICreator/MiniGPT2-22M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SmallAICreator/MiniGPT2-22M-GGUF:F16

Ollama
How to use SmallAICreator/MiniGPT2-22M-GGUF with Ollama:
```
ollama run hf.co/SmallAICreator/MiniGPT2-22M-GGUF:F16
```
Unsloth Desktop

How to use SmallAICreator/MiniGPT2-22M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SmallAICreator/MiniGPT2-22M-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SmallAICreator/MiniGPT2-22M-GGUF with Docker Model Runner:
```
docker model run hf.co/SmallAICreator/MiniGPT2-22M-GGUF:F16
```

Lemonade

How to use SmallAICreator/MiniGPT2-22M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SmallAICreator/MiniGPT2-22M-GGUF:F16

Run and chat with the model

lemonade run user.MiniGPT2-22M-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use SmallAICreator/MiniGPT2-22M-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 SmallAICreator/MiniGPT2-22M-GGUF:F16

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 SmallAICreator/MiniGPT2-22M-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SmallAICreator/MiniGPT2-22M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SmallAICreator/MiniGPT2-22M-GGUF:F16

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 "SmallAICreator/MiniGPT2-22M-GGUF:F16" \
  --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"

MiniGPT2-22M (GGUF, F16)

A 22M-parameter language model trained from scratch by SmallAICreator / UltraLabs, small enough to chat on a phone.

File: MiniGPT2-22M-F16.gguf (44.6 MB), for llama.cpp, PocketPal, LM Studio, Ollama, etc.
Chat template is embedded, so apps pick up the right format automatically.

Model


Parameters	22.03M (15.7M non-embedding)
Architecture	Llama-style decoder: 10 layers, d=384, 6 heads / 2 KV heads (GQA), SwiGLU 1024, RoPE, RMSNorm, tied embeddings
Context	1024 tokens
Tokenizer	16,384-token byte-level BPE (trained for this model)
Training tokens	~26.5B (single pass, no repetition)
Data	FineWeb-Edu, Cosmopedia-v2, SlimPajama, FineMath, Python code, HTML, plus a chat/instruction blend distilled from a larger model, mixed in during the final part of training
Optimizer	Muon (hidden matrices) + AdamW (embeddings/norms)
Hardware	TPU v5e-8, 7 hours

Prompt format

<|system|>You are a helpful assistant.<|end|><|user|>What is the capital of France?<|end|><|assistant|>

No BOS token. The model ends its turn with <|end|>.

llama-cli -m MiniGPT2-22M-F16.gguf -cnv

Tool calling

The embedded chat template supports tools (OpenAI-style tools / tool_calls), so apps with a tool picker enable it automatically. The model emits:

<tool_call>
{"name": "web_search", "arguments": {"query": "Tokyo weather today"}}
</tool_call>

Tool results go back as a tool message, which the template renders as a <tool_response> turn. The model then answers from the result. It was trained on calculator, web_search, fetch_url, search_knowledge_base and execute_javascript calls. Remember it's 22M, so double-check arguments.

Examples

Who are you? I'm MiniGPT2, a tiny 22M-parameter model from UltraLabs. I'm small, so I get facts wrong and I'm weak at multi-step arithmetic.

What is the capital of France? The capital of France is Paris.

Write a haiku about the ocean. Waves whisper softly / rolling onto quiet sand / the ocean breathes and rests.

Benchmarks

0-shot, lm-evaluation-harness 0.4.13, fp32. Every model was run through the same harness. Our Supra-50M run reproduces that model's published numbers exactly.

Task	MiniGPT2 (22M)	Pythia-70M	Supra-50M
ARC-Easy (acc)	42.2	37.5	52.2
ARC-Easy (acc_norm)	40.0	35.2	46.0
ARC-Challenge (acc_norm)	23.1	21.9	25.0
HellaSwag (acc_norm)	28.2	27.4	31.8
PIQA (acc_norm)	58.1	59.2	62.1
SciQ (acc)	66.4	64.0	77.2
Winogrande (acc)	50.0	53.0	51.0
BLiMP (acc)	74.2	74.2	76.3
LAMBADA OpenAI (acc)	23.1	22.7	25.9
LAMBADA standard (acc)	13.5	15.5	17.2
WikiText (bits/byte, lower is better)	1.176	1.080	1.027

MiniGPT2 beats Pythia-70M (3.2x its size) on 6 of 11 tasks and ties BLiMP. It trails Supra-50M, a model 2.3x larger.

Conversion

Converted from the original JAX checkpoint to HF Llama, then to GGUF. Verified:

The HF model matches the training forward pass (max logit diff 4e-5).
llama.cpp tokenization matches the HF tokenizer exactly.
The F16 GGUF's logits match HF (top-1 agreement 100%, mean KL 7.6e-6).

Limitations

This is a 22M model. It makes factual mistakes, is weak at arithmetic and multi-step reasoning, and can be verbose. Do not rely on it for anything important.

Downloads last month: 133

GGUF

Model size

22M params

Architecture

llama

Hardware compatibility

16-bit