Instructions to use regolo/brick-complexity-2-max-BF16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use regolo/brick-complexity-2-max-BF16-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="regolo/brick-complexity-2-max-BF16-GGUF",
	filename="brick-complexity-2-max-BF16.gguf",
)

llm.create_chat_completion(
	messages = "\"I like you. I love you\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use regolo/brick-complexity-2-max-BF16-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

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 regolo/brick-complexity-2-max-BF16-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

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 regolo/brick-complexity-2-max-BF16-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

Use Docker

docker model run hf.co/regolo/brick-complexity-2-max-BF16-GGUF:BF16

LM Studio
Jan
Ollama
How to use regolo/brick-complexity-2-max-BF16-GGUF with Ollama:
```
ollama run hf.co/regolo/brick-complexity-2-max-BF16-GGUF:BF16
```

Unsloth Studio new

How to use regolo/brick-complexity-2-max-BF16-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 regolo/brick-complexity-2-max-BF16-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 regolo/brick-complexity-2-max-BF16-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for regolo/brick-complexity-2-max-BF16-GGUF to start chatting

Pi new

How to use regolo/brick-complexity-2-max-BF16-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

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": "regolo/brick-complexity-2-max-BF16-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use regolo/brick-complexity-2-max-BF16-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf regolo/brick-complexity-2-max-BF16-GGUF:BF16

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 regolo/brick-complexity-2-max-BF16-GGUF:BF16

Run Hermes

hermes

Docker Model Runner
How to use regolo/brick-complexity-2-max-BF16-GGUF with Docker Model Runner:
```
docker model run hf.co/regolo/brick-complexity-2-max-BF16-GGUF:BF16
```

Lemonade

How to use regolo/brick-complexity-2-max-BF16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull regolo/brick-complexity-2-max-BF16-GGUF:BF16

Run and chat with the model

lemonade run user.brick-complexity-2-max-BF16-GGUF-BF16

List all available models

lemonade list

Brick Complexity Classifier v2: `max` (BF16 GGUF)

What is this?

BF16 quantized GGUF of regolo/brick-complexity-2-max. A small classifier that scores each prompt as easy / medium / hard so a router can dispatch it to the right tier of a model pool.

The max variant is optimized for routing accuracy: it gives the sharpest easy/medium/hard split so hard queries reliably reach the strongest tier.

Regolo.ai | Original Model | Brick SR1 on GitHub

Model Details

Property	Value
Quantization	BF16
File	`brick-complexity-2-max-BF16.gguf`
Size	1.5 GB
Bits per weight	16.0
Original model	regolo/brick-complexity-2-max
Base model	Qwen/Qwen3.5-0.8B
Output classes	3 (`easy`, `medium`, `hard`)
License	CC BY-NC 4.0

This is a full merged model (base Qwen3.5-0.8B + LoRA adapter merged and quantized), no separate adapter loading needed.

All Available Quantizations

Model	Quant	Size	BPW
BF16-GGUF	BF16	1.5 GB	16.0
Q8_0-GGUF	Q8_0	775 MB	8.0
Q4_K_M-GGUF	Q4_K_M	494 MB	5.5

Usage with llama.cpp

huggingface-cli download regolo/brick-complexity-2-max-BF16-GGUF brick-complexity-2-max-BF16.gguf --local-dir ./models

./llama-cli -m ./models/brick-complexity-2-max-BF16.gguf \
    -p "<|im_start|>system
You are a query difficulty classifier for an LLM routing system.
Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
Respond with ONLY one word: easy, medium, or hard.<|im_end|>
<|im_start|>user
Classify: What is the capital of France?<|im_end|>
<|im_start|>assistant
" \
    -n 5 --temp 0

Usage with Ollama

cat > Modelfile <<EOF
FROM ./brick-complexity-2-max-BF16.gguf

SYSTEM """You are a query difficulty classifier for an LLM routing system.
Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
Respond with ONLY one word: easy, medium, or hard."""

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
Classify: {{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

PARAMETER temperature 0
PARAMETER num_predict 5
EOF

ollama create brick-complexity-2-max -f Modelfile
ollama run brick-complexity-2-max "Design a distributed consensus algorithm"
# Output: hard

Usage with vLLM

from vllm import LLM, SamplingParams

llm = LLM(model="regolo/brick-complexity-2-max-BF16-GGUF")
sp = SamplingParams(temperature=0, max_tokens=5)

prompt = """<|im_start|>system
You are a query difficulty classifier for an LLM routing system.
Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
Respond with ONLY one word: easy, medium, or hard.<|im_end|>
<|im_start|>user
Classify: Explain the rendering equation from radiometric first principles<|im_end|>
<|im_start|>assistant
"""

out = llm.generate([prompt], sp)
print(out[0].outputs[0].text.strip())
# Output: hard

Note on GGUF Inference

The GGUF model uses generative text output ("easy"/"medium"/"hard") rather than logit-based classification used by the original LoRA adapter. For maximum accuracy, use the original LoRA adapter with PEFT.

About Brick

Regolo.ai is the EU-sovereign LLM inference platform built on Seeweb infrastructure. Brick is our open-source semantic routing system that intelligently distributes queries across model pools, optimizing for cost, latency, and quality.

Website | Docs | GitHub | Discord