Instructions to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AiAsistent/xthos-v2-the-sovereign-architect-GGUF", dtype="auto")

llama-cpp-python

How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AiAsistent/xthos-v2-the-sovereign-architect-GGUF",
	filename="xthos-v2.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 AiAsistent/xthos-v2-the-sovereign-architect-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 AiAsistent/xthos-v2-the-sovereign-architect-GGUF
# Run inference directly in the terminal:
llama cli -hf AiAsistent/xthos-v2-the-sovereign-architect-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AiAsistent/xthos-v2-the-sovereign-architect-GGUF
# Run inference directly in the terminal:
llama cli -hf AiAsistent/xthos-v2-the-sovereign-architect-GGUF

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 AiAsistent/xthos-v2-the-sovereign-architect-GGUF
# Run inference directly in the terminal:
./llama-cli -hf AiAsistent/xthos-v2-the-sovereign-architect-GGUF

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 AiAsistent/xthos-v2-the-sovereign-architect-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AiAsistent/xthos-v2-the-sovereign-architect-GGUF

Use Docker

docker model run hf.co/AiAsistent/xthos-v2-the-sovereign-architect-GGUF

LM Studio
Jan
Ollama
How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with Ollama:
```
ollama run hf.co/AiAsistent/xthos-v2-the-sovereign-architect-GGUF
```

Unsloth Studio

How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF 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 AiAsistent/xthos-v2-the-sovereign-architect-GGUF 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 AiAsistent/xthos-v2-the-sovereign-architect-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AiAsistent/xthos-v2-the-sovereign-architect-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with Docker Model Runner:
```
docker model run hf.co/AiAsistent/xthos-v2-the-sovereign-architect-GGUF
```

Lemonade

How to use AiAsistent/xthos-v2-the-sovereign-architect-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AiAsistent/xthos-v2-the-sovereign-architect-GGUF

Run and chat with the model

lemonade run user.xthos-v2-the-sovereign-architect-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

🏛️ χθos v2 — The Sovereign Architect (GGUF Version)

This repository provides the GGUF quantized weights for $\chi\theta os$ v2, optimized for local inference via llama.cpp, LM Studio, Jan, or other compatible frameworks.

$\chi\theta os$ v2 is an ultra-high-density 4B parameter reasoning model designed to prove that strategic depth and ontological nuance can be achieved at scale through specialized "Deep Convergence" training.

🔗 Quick Links

Original Model (Full Weights): AiAsistent/xthos-v2-the-sovereign-architect
Ollama Version: aiasistentworld/xthos-v2 (ollama run aiasistentworld/xthos-v2)
Official Documentation & Research: LLMResearch.net

🚀 Push the Frontier: Community Challenge

We encourage users to χθos v2 to its absolute limits**

Research Call: χθos v2

Whether you are testing its Infinite Recursive Reasoning
(demonstrated to handle 500+ turn autonomous dialogues)
or its capacity for unfiltered Realpolitik analysis, we want to see your results.

Report your discoveries, emergent behaviors, or suggestions for v3 at:
👉 LLMResearch.net

🔬 Upcoming Research: The 400B Comparison

Can a 4B parameter "Architect" match the strategic logic of a 400B+ giant?

I am currently conducting a rigorous comparative analysis between χθos v2
and industry leaders such as:

DeepSeek 400+B
GPT-4/5
GLM-4.7 (355B)

Preliminary tests show χθos v2 competing as an equal in:

Systemic strategy
Paradox resolution

📢 Full results will be published soon on LLMResearch.net.

@misc{xthos-v2-architect,
  author = {AlexH},
  organization = {LLMResearch.net},
  title = xthos v2 - The Sovereign Architect},
  year = {2026},
  url = {https://llmresearch.net}
}