Instructions to use SZLHOLDINGS/A11OY-MINI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SZLHOLDINGS/A11OY-MINI 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 SZLHOLDINGS/A11OY-MINI:F16
# Run inference directly in the terminal:
llama cli -hf SZLHOLDINGS/A11OY-MINI:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SZLHOLDINGS/A11OY-MINI:F16
# Run inference directly in the terminal:
llama cli -hf SZLHOLDINGS/A11OY-MINI: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 SZLHOLDINGS/A11OY-MINI:F16
# Run inference directly in the terminal:
./llama-cli -hf SZLHOLDINGS/A11OY-MINI: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 SZLHOLDINGS/A11OY-MINI:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SZLHOLDINGS/A11OY-MINI:F16

Use Docker

docker model run hf.co/SZLHOLDINGS/A11OY-MINI:F16

LM Studio
Jan

vLLM

How to use SZLHOLDINGS/A11OY-MINI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SZLHOLDINGS/A11OY-MINI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SZLHOLDINGS/A11OY-MINI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SZLHOLDINGS/A11OY-MINI:F16

Ollama
How to use SZLHOLDINGS/A11OY-MINI with Ollama:
```
ollama run hf.co/SZLHOLDINGS/A11OY-MINI:F16
```
Unsloth Desktop

How to use SZLHOLDINGS/A11OY-MINI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SZLHOLDINGS/A11OY-MINI: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": "SZLHOLDINGS/A11OY-MINI:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SZLHOLDINGS/A11OY-MINI with Docker Model Runner:
```
docker model run hf.co/SZLHOLDINGS/A11OY-MINI:F16
```

Lemonade

How to use SZLHOLDINGS/A11OY-MINI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SZLHOLDINGS/A11OY-MINI:F16

Run and chat with the model

lemonade run user.A11OY-MINI-F16

List all available models

lemonade list

Hermes Agent

How to use SZLHOLDINGS/A11OY-MINI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SZLHOLDINGS/A11OY-MINI: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 SZLHOLDINGS/A11OY-MINI:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SZLHOLDINGS/A11OY-MINI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SZLHOLDINGS/A11OY-MINI: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 "SZLHOLDINGS/A11OY-MINI: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"

A11OY-MINI

KANCHAY · Doctrine v11 · Lean 749/14/163 · Λ = Conjecture 1 (advisory) · a-11-oy.com

GGUFs are on this repo. GGUF AVAILABLE. Bytes MEASURED (size + sha256 below, ATELIER-verified). Evals none-this-run. Not MEASURED as an eval. publication_eligible: false. Quality ROADMAP in prose only. Lab load forbidden. GPU UNAVAILABLE.

SKU of live SZLHOLDINGS/chaski merged shard 1c55df8. Not a new train. Not SZLHOLDINGS/chaski-5050. Not a Hub base_model_relation: quantized child until a Chaski eval gate passes.

The cut

A11oy is a Space and a substrate. The mini is the voice you can actually load. Not the organ. Not the mesh.

A governed command voice that fits in llama.cpp.

Silhouette → leave → SZL

Leader	Take, then tweak
Anthropic	A small Claude-shaped mouth with a much stricter constitution.
NVIDIA	A NIM-less local runtime.
Unsloth	GGUF path.

Nobody else ships this combination. That is the point of a one-of-one.

Intended use

Local doctrine voice. Proposal-only if wired to tools.

Limitations

Derived quant.
Not a11oy-v19-substrate.

Canonical GitHub: szl-holdings/szl-forge


SKU	`SZLHOLDINGS/A11OY-MINI`
Parent	live `SZLHOLDINGS/chaski` merged shard `1c55df8652e9d0f7b84356b1e2d54849165ae884`
Not parent	`SZLHOLDINGS/chaski-5050`
Silhouette base	`Qwen/Qwen3.5-0.8B` (named in prose only; no YAML `base_model`)
F16	`a11oy-mini-f16.gguf` 1557662240 sha256 `a5df00e4e3ca07f65a4b43aad4ef1505625952a3105e6dcc0dba87f2fa35fc57` MEASURED
Q4_K_M	`a11oy-mini-q4_k_m.gguf` 541903392 sha256 `06136ba385b2e052cf4cdb3dc8d333948e0b612bd15a541b314e170399c2faa6` MEASURED
Convert	llama.cpp F16 then Q4_K_M
Banned	Direct safetensors→Ollama. Lab load.
Evals	none-this-run. Not 5/5. Bytes MEASURED is not an eval.
Quality	ROADMAP (prose only; YAML tag omitted)
Publication	`publication_eligible: false`
Lab	Forbidden. House CPU lab stays Khipu GGUF. Do not load this SKU in inference-lab.
License	Apache-2.0
Doctrine	v11 LOCKED. Seed 11. Λ = Conjecture 1 (advisory, never a theorem).

What this is NOT

Not a published model eval and not 5/5
Not chaski-5050
Not a base_model_relation: quantized Hub child (Chaski eval gate has not passed)
Not a lab pin and not loadable in the house lab
Not a tokens/s claim
Not a new train and not a third LLM

Downloads last month: -

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

16-bit