Instructions to use georgeanton/alice-m1-cortex-4.5b-3.4gb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use georgeanton/alice-m1-cortex-4.5b-3.4gb 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 georgeanton/alice-m1-cortex-4.5b-3.4gb
# Run inference directly in the terminal:
llama cli -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf georgeanton/alice-m1-cortex-4.5b-3.4gb
# Run inference directly in the terminal:
llama cli -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

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-m1-cortex-4.5b-3.4gb
# Run inference directly in the terminal:
./llama-cli -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

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-m1-cortex-4.5b-3.4gb
# Run inference directly in the terminal:
./build/bin/llama-cli -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

Use Docker

docker model run hf.co/georgeanton/alice-m1-cortex-4.5b-3.4gb

LM Studio
Jan
Ollama
How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with Ollama:
```
ollama run hf.co/georgeanton/alice-m1-cortex-4.5b-3.4gb
```
Unsloth Desktop

How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

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": "georgeanton/alice-m1-cortex-4.5b-3.4gb"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with Docker Model Runner:
```
docker model run hf.co/georgeanton/alice-m1-cortex-4.5b-3.4gb
```

Lemonade

How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull georgeanton/alice-m1-cortex-4.5b-3.4gb

Run and chat with the model

lemonade run user.alice-m1-cortex-4.5b-3.4gb-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

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-m1-cortex-4.5b-3.4gb

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use georgeanton/alice-m1-cortex-4.5b-3.4gb with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf georgeanton/alice-m1-cortex-4.5b-3.4gb

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 "georgeanton/alice-m1-cortex-4.5b-3.4gb" \
  --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"

georgeanton commited on May 9

Commit

30aba6b

verified ·

1 Parent(s): aafca89

SIFTA public cortex distro update - 2026-05-09

Browse files

Files changed (5) hide show

.gitattributes +1 -0
Modelfile +8 -0
README.md +21 -0
alice-m1-cortex-4.5b-3.4gb.gguf +3 -0
provenance.json +13 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+alice-m1-cortex-4.5b-3.4gb.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile ADDED Viewed

	@@ -0,0 +1,8 @@

+FROM ./alice-m1-cortex-4.5b-3.4gb.gguf
+TEMPLATE {{ .Prompt }}
+RENDERER qwen3.5
+PARSER qwen3.5
+PARAMETER presence_penalty 1.5
+PARAMETER temperature 1
+PARAMETER top_k 20
+PARAMETER top_p 0.95

README.md ADDED Viewed

	@@ -0,0 +1,21 @@

+# Alice M1 Cortex 4.5B 3.4GB
+8GB-safe SIFTA cortex/scout tag:
+```bash
+ollama create alice-m1-cortex-4.5b-3.4gb:latest -f Modelfile
+```
+This model is the safer local cortex for Mac Mini / M1 Sentry-class nodes where
+the M5 cortex does not fit comfortably in RAM.
+## Role
+Use this tag for low-RAM SIFTA nodes, scouts, and local fallback reasoning. It
+is not the M5 Foundry primary cortex when `alice-m5-cortex-8b-6.3gb:latest`
+is available.
+## Local State Boundary
+This model package is public species DNA. It must not include raw `.sifta_state/`
+selfhood, contacts, owner memory, camera frames, or private receipts.

alice-m1-cortex-4.5b-3.4gb.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:464c1dda6a052d909b11d20c31bcb21060e969e334716ba8ed7abf64ca1be10f
+size 3376217632

provenance.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "truth_label": "SIFTA_PUBLIC_MODEL_PROVENANCE",
+  "tag": "alice-m1-cortex-4.5b-3.4gb:latest",
+  "hf_repo": "georgeanton/alice-m1-cortex-4.5b-3.4gb",
+  "ollama_blob": "sha256-464c1dda6a052d909b11d20c31bcb21060e969e334716ba8ed7abf64ca1be10f",
+  "renderer": "qwen3.5",
+  "verified_at": "2026-05-09",
+  "verified_by": "C55M@codex",
+  "notes": [
+    "8GB-safe M1/Sentry cortex lane.",
+    "Use as scout/fallback on smaller nodes."
+  ]
+}