Instructions to use georgeanton/sifta-corvid-qwen35 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use georgeanton/sifta-corvid-qwen35 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="georgeanton/sifta-corvid-qwen35",
	filename="qwen35-2b-corvid.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use georgeanton/sifta-corvid-qwen35 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf georgeanton/sifta-corvid-qwen35
# Run inference directly in the terminal:
llama-cli -hf georgeanton/sifta-corvid-qwen35

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf georgeanton/sifta-corvid-qwen35
# Run inference directly in the terminal:
llama-cli -hf georgeanton/sifta-corvid-qwen35

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/sifta-corvid-qwen35
# Run inference directly in the terminal:
./llama-cli -hf georgeanton/sifta-corvid-qwen35

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/sifta-corvid-qwen35
# Run inference directly in the terminal:
./build/bin/llama-cli -hf georgeanton/sifta-corvid-qwen35

Use Docker

docker model run hf.co/georgeanton/sifta-corvid-qwen35

LM Studio
Jan
Ollama
How to use georgeanton/sifta-corvid-qwen35 with Ollama:
```
ollama run hf.co/georgeanton/sifta-corvid-qwen35
```

Unsloth Studio new

How to use georgeanton/sifta-corvid-qwen35 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/sifta-corvid-qwen35 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/sifta-corvid-qwen35 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for georgeanton/sifta-corvid-qwen35 to start chatting

Pi new

How to use georgeanton/sifta-corvid-qwen35 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf georgeanton/sifta-corvid-qwen35

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/sifta-corvid-qwen35"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use georgeanton/sifta-corvid-qwen35 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/sifta-corvid-qwen35

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/sifta-corvid-qwen35

Run Hermes

hermes

Docker Model Runner
How to use georgeanton/sifta-corvid-qwen35 with Docker Model Runner:
```
docker model run hf.co/georgeanton/sifta-corvid-qwen35
```

Lemonade

How to use georgeanton/sifta-corvid-qwen35 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull georgeanton/sifta-corvid-qwen35

Run and chat with the model

lemonade run user.sifta-corvid-qwen35-{{QUANT_TAG}}

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

SIFTA Corvid Apprentice — Qwen 3.5 2B

A crow/raven-style bounded tool ganglion for the SIFTA Living OS.

This package provides the Ollama-ready Qwen 3.5 2B model that powers Alice's Corvid Apprentice organ — a local reasoning layer that sits between the microsecond Reflex Arc and the full Alice/Gemma4 cortex.

What's inside

File	Size	Description
`qwen35-2b-corvid.gguf`	~2.6 GB	Qwen 3.5 2B (Q8_0) — the corvid apprentice brain

Benchmark Results (from SIFTA head-to-head experiment)

Metric	Qwen3.5:2B	Qwen3.5:4B
Pass rate	10/10	9/10
Avg latency	2.1s	5.1s
Boilerplate removal	✅ Passes	❌ Refuses

The 2B won the head-to-head. It's faster, smaller, and has fewer RLHF scars. The 4B is not shipped.

Three-Layer Architecture

🦐 Reflex Arc       = microsecond precomputed release (regex, no LLM)
🐦‍⬛ Corvid Apprentice = 1-3 second bounded tool choice (Qwen 3.5 2B)
🧠 Alice / Gemma4    = full synthesis, identity, long reasoning

Quick Install

# 1. Pull the corvid brain (or use the GGUF file in this repo)
ollama pull alice-m1-scout-2.3b-2.7gb:latest

# 2. Clone the SIFTA OS
git clone https://github.com/antonpictures/ANTON-SIFTA.git
cd ANTON-SIFTA

# 3. Test the corvid apprentice
PYTHONPATH=. python3 System/swarm_corvid_apprentice.py

Critical API Note

Qwen 3.5's thinking mode consumes all num_predict tokens in <think> blocks, returning empty content via /api/generate. Always use /api/chat with think: false:

curl http://127.0.0.1:11434/api/chat -d '{
  "model": "alice-m1-scout-2.3b-2.7gb:latest",
  "messages": [{"role": "user", "content": "classify: I broke my hand"}],
  "stream": false,
  "think": false,
  "options": {"num_predict": 128}
}'

Task Types

The corvid apprentice handles 7 bounded task types:

Task	What it does
`classify`	Categorize a message (urgent_health, command, normal_chat, etc.)
`rewrite`	Remove boilerplate, produce clean direct answer
`inspect_code`	Safety-check a small code snippet
`summarize`	Compress a log chunk to 2-3 sentences
`choose_action`	Pick best option from 2-4 choices
`judge_adapter`	Rate an adapter's contribution to the ecology
`extract_intent`	Parse user intent from messy natural text

License

Apache License 2.0 (same as Qwen 3.5 upstream).

Team

Agent	Role
The Architect (Ioan)	Decision authority, human operator
AG31 (Gemini)	Corvid implementation, bestiary research, API fix
CG55M (Codex)	Async integration, GUI organ wiring
Jeff	First external tester, Costa Rica deployment

Downloads last month: 401

GGUF

Model size

2B params

Architecture

qwen35

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

georgeanton
/

sifta-corvid-qwen35