Instructions to use petedavis/bmk-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use petedavis/bmk-models 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 petedavis/bmk-models:BF16
# Run inference directly in the terminal:
llama cli -hf petedavis/bmk-models:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf petedavis/bmk-models:BF16
# Run inference directly in the terminal:
llama cli -hf petedavis/bmk-models: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 petedavis/bmk-models:BF16
# Run inference directly in the terminal:
./llama-cli -hf petedavis/bmk-models: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 petedavis/bmk-models:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf petedavis/bmk-models:BF16

Use Docker

docker model run hf.co/petedavis/bmk-models:BF16

LM Studio
Jan

vLLM

How to use petedavis/bmk-models with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/petedavis/bmk-models:BF16

Ollama
How to use petedavis/bmk-models with Ollama:
```
ollama run hf.co/petedavis/bmk-models:BF16
```
Unsloth Desktop

How to use petedavis/bmk-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf petedavis/bmk-models:BF16

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": "petedavis/bmk-models:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use petedavis/bmk-models with Docker Model Runner:
```
docker model run hf.co/petedavis/bmk-models:BF16
```

Lemonade

How to use petedavis/bmk-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull petedavis/bmk-models:BF16

Run and chat with the model

lemonade run user.bmk-models-BF16

List all available models

lemonade list

Hermes Agent

How to use petedavis/bmk-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf petedavis/bmk-models: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 petedavis/bmk-models:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use petedavis/bmk-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf petedavis/bmk-models:BF16

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 "petedavis/bmk-models:BF16" \
  --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"

KAT-Coder-V2.5-Dev — bmk asymmetric quantization (IQ2_XXS/Q2_K experts, Q8_0 dense)

Asymmetric GGUF quantization of Kwaipilot/KAT-Coder-V2.5-Dev (qwen35moe: 34.7B total / ~3B active, 40 layers, 256 routed experts top-8, 1 shared expert, GDN hybrid attention, 262144 ctx), built for the bmk bare-metal inference engine.

Quantization map

Component	Type
Routed experts gate/up (40 × 256)	IQ2_XXS
Routed experts down (40 × 256)	Q2_K
Attention incl. GDN/SSM, shared experts, embeddings, output head	Q8_0

Importance-matrix calibrated (Kwaipilot imatrix, 510 entries / 802 chunks). File size: 10.9 GiB. Designed for 8/12/16 GB VRAM cards via expert-granular streaming (only the top-8 routed experts per layer are loaded).

Usage

Run with bmk:

bash download_model.sh bmk-q2
LD_LIBRARY_PATH=vendor/cuda-runtime ./bmk -m models/kat-coder-asym.gguf -p "..." -n 64

llama.cpp-compatible GGUF; the tensor layout follows the standard qwen35moe architecture.

Downloads last month: 53

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

16-bit

View +1 variant

Model tree for petedavis/bmk-models

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Quantized

(67)

this model