Instructions to use badtheorylabs/BTL-3-Compact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use badtheorylabs/BTL-3-Compact with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="badtheorylabs/BTL-3-Compact",
	filename="model/BTL-3-Compact-AVQ2.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use badtheorylabs/BTL-3-Compact 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 badtheorylabs/BTL-3-Compact
# Run inference directly in the terminal:
llama cli -hf badtheorylabs/BTL-3-Compact

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf badtheorylabs/BTL-3-Compact
# Run inference directly in the terminal:
llama cli -hf badtheorylabs/BTL-3-Compact

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 badtheorylabs/BTL-3-Compact
# Run inference directly in the terminal:
./llama-cli -hf badtheorylabs/BTL-3-Compact

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 badtheorylabs/BTL-3-Compact
# Run inference directly in the terminal:
./build/bin/llama-cli -hf badtheorylabs/BTL-3-Compact

Use Docker

docker model run hf.co/badtheorylabs/BTL-3-Compact

LM Studio
Jan

vLLM

How to use badtheorylabs/BTL-3-Compact with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "badtheorylabs/BTL-3-Compact"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "badtheorylabs/BTL-3-Compact",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/badtheorylabs/BTL-3-Compact

Ollama
How to use badtheorylabs/BTL-3-Compact with Ollama:
```
ollama run hf.co/badtheorylabs/BTL-3-Compact
```

Unsloth Studio

How to use badtheorylabs/BTL-3-Compact 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 badtheorylabs/BTL-3-Compact 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 badtheorylabs/BTL-3-Compact to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for badtheorylabs/BTL-3-Compact to start chatting

How to use badtheorylabs/BTL-3-Compact with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf badtheorylabs/BTL-3-Compact

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": "badtheorylabs/BTL-3-Compact"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use badtheorylabs/BTL-3-Compact with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf badtheorylabs/BTL-3-Compact

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 badtheorylabs/BTL-3-Compact

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use badtheorylabs/BTL-3-Compact with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf badtheorylabs/BTL-3-Compact

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 "badtheorylabs/BTL-3-Compact" \
  --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"

Docker Model Runner
How to use badtheorylabs/BTL-3-Compact with Docker Model Runner:
```
docker model run hf.co/badtheorylabs/BTL-3-Compact
```

Lemonade

How to use badtheorylabs/BTL-3-Compact with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull badtheorylabs/BTL-3-Compact

Run and chat with the model

lemonade run user.BTL-3-Compact-{{QUANT_TAG}}

List all available models

lemonade list

BTL-3-Compact / docs /btl-3-compact-gguf-exporter.md

affableiq

Publish BTL-3 Compact package metadata

274ffba verified 8 days ago

preview code

Raw

History Blame Contribute Delete

2.46 kB

BTL-3 Compact GGUF exporter

Scope

The exporter turns the frozen BTL-3 Compact package into the tensor contract consumed by the custom Qwen3.6 llama.cpp backend. It never reconstructs a dense decoder. Safetensors are mmap-backed and materialized one tensor at a time. Every one of the 158 source files is size- and SHA-256-checked against the frozen package manifest before planning or writing.

It exports:

standard Qwen3.6 small-state tensors with official converter semantics;
AVQ2 codes, affines, and exact Torch-seeded sign vectors;
affine-INT4 codes, scales, and zero points;
the two final INT4 demotions in place of their superseded BF16 islands;
frozen BF16 islands;
the rank-8 behavior LoRA;
AVQ2 embedding and output tensors, rescued embedding rows, and head residual.

Verified planning result

The full dry-run plans 2,416 tensors and 8,381,262,032 tensor bytes. The 170,510,920-byte reduction from the source package is expected: the package retains two superseded BF16 island files for provenance, while the export emits only their final INT4 demotions.

The exporter reports no unsupported representations and no native-runtime contract gaps.

Numerical conformance

Three representative layers were exported so every decoder representation was materialized:

Layer	Coverage	Tensors	Bytes	Payloads verified
13	AVQ2, BF16 island, final INT4 demotion	28	322,295,104	28/28
40	AVQ2, small state, behavior LoRA	44	98,427,808	44/44
47	AVQ2, standard affine INT4, behavior LoRA	35	122,932,064	35/35

Every tensor passed:

canonical-name equality;
source-shape equality;
exact GGUF storage-type equality;
exact raw payload-byte equality after required Qwen transformations;
exact regeneration of seeded signs.

The layer-40 artifact SHA-256 is e621b4cdb1e3f25cdde514427b14cd6d27bacbe72ad5850468311c693d4d79f7.

This one-layer artifact is not a runnable model. A full export was deliberately not started at this gate.

Commands

.venv/bin/python tools/export_btl3_compact_gguf.py \
  --source /path/to/BTL-3/compact \
  --dry-run \
  --report artifacts/btl3-compact-gguf-dry-run.json

.venv/bin/python tools/export_btl3_compact_gguf.py \
  --source /path/to/BTL-3/compact \
  --conformance-layer 40 \
  --output artifacts/conformance/btl-3-compact-layer40.gguf \
  --report artifacts/conformance/btl-3-compact-layer40.report.json