Instructions to use georgeanton/alice-m5-cortex-8b-6.3gb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use georgeanton/alice-m5-cortex-8b-6.3gb with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="georgeanton/alice-m5-cortex-8b-6.3gb",
	filename="alice-m5-cortex-8b-6.3gb.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use georgeanton/alice-m5-cortex-8b-6.3gb with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf georgeanton/alice-m5-cortex-8b-6.3gb
# Run inference directly in the terminal:
llama-cli -hf georgeanton/alice-m5-cortex-8b-6.3gb

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf georgeanton/alice-m5-cortex-8b-6.3gb
# Run inference directly in the terminal:
llama-cli -hf georgeanton/alice-m5-cortex-8b-6.3gb

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 georgeanton/alice-m5-cortex-8b-6.3gb
# Run inference directly in the terminal:
./llama-cli -hf georgeanton/alice-m5-cortex-8b-6.3gb

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 georgeanton/alice-m5-cortex-8b-6.3gb
# Run inference directly in the terminal:
./build/bin/llama-cli -hf georgeanton/alice-m5-cortex-8b-6.3gb

Use Docker

docker model run hf.co/georgeanton/alice-m5-cortex-8b-6.3gb

LM Studio
Jan
Ollama
How to use georgeanton/alice-m5-cortex-8b-6.3gb with Ollama:
```
ollama run hf.co/georgeanton/alice-m5-cortex-8b-6.3gb
```

Unsloth Studio

How to use georgeanton/alice-m5-cortex-8b-6.3gb 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 georgeanton/alice-m5-cortex-8b-6.3gb 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 georgeanton/alice-m5-cortex-8b-6.3gb to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for georgeanton/alice-m5-cortex-8b-6.3gb to start chatting

How to use georgeanton/alice-m5-cortex-8b-6.3gb with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf georgeanton/alice-m5-cortex-8b-6.3gb

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": "georgeanton/alice-m5-cortex-8b-6.3gb"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use georgeanton/alice-m5-cortex-8b-6.3gb with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf georgeanton/alice-m5-cortex-8b-6.3gb

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 georgeanton/alice-m5-cortex-8b-6.3gb

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use georgeanton/alice-m5-cortex-8b-6.3gb with Docker Model Runner:
```
docker model run hf.co/georgeanton/alice-m5-cortex-8b-6.3gb
```

Lemonade

How to use georgeanton/alice-m5-cortex-8b-6.3gb with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull georgeanton/alice-m5-cortex-8b-6.3gb

Run and chat with the model

lemonade run user.alice-m5-cortex-8b-6.3gb-{{QUANT_TAG}}

List all available models

lemonade list

Alice M5 Cortex 8B 6.3GB

Primary M5 SIFTA cortex tag:

ollama create alice-m5-cortex-8b-6.3gb:latest -f Modelfile

This is the promoted M5 cortex used by Alice on the Foundry node. It is a SIFTA-owned Ollama tag and does not use the retired LoRA candidate.

Live Probe

Verified on 2026-05-09:

architecture: Gemma4
parameters: 8B
context length: 131072
runtime context: 8192
capabilities reported by ollama show: completion, vision, audio, tools, thinking
/api/chat with think:false answered both text and image prompts

SIFTA Runtime Note

Alice's Talk path uses /api/chat with think:false. Raw calls that omit this can spend the whole output budget in the thinking field and return blank assistant content.

SIFTA Field Breakthrough

The current SIFTA public repo includes a stigmergic field breakthrough brief: https://github.com/antonpictures/ANTON-SIFTA/blob/main/Documents/CARLTON_STIGMERGIC_FIELD_BREAKTHROUGH_2026-05-11.md

The cortex is only one organ in that system. The field mechanism itself runs in the Python body: Bell analogue simulator, kernel scheduler, and hippocampus. Credit boundary: Bell/CHSH/Hall/pilot-wave/stigmergy literature grounds the analogy; SIFTA claims a receipt-backed classical contextual analogue, not a proof of the physical cause of quantum nonlocality.

Local State Boundary

This model package is public species DNA. It must not include a node's raw .sifta_state/ memory, contacts, owner traces, camera frames, or private receipts.

Downloads last month: 261

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support