Instructions to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP",
	filename="Kwaipilot_KAT-Coder-V2.5-Dev-IQ4_XS.bartowski.mtp.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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP 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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

Use Docker

docker model run hf.co/thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

LM Studio
Jan
Ollama
How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with Ollama:
```
ollama run hf.co/thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
```

Unsloth Studio

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP 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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP 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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP to start chatting

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

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": "thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

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 "thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS" \
  --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 thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with Docker Model Runner:
```
docker model run hf.co/thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS
```

Lemonade

How to use thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thread13/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP:IQ4_XS

Run and chat with the model

lemonade run user.Kwaipilot_KAT-Coder-V2.5-Dev-GGUF-MTP-IQ4_XS

List all available models

lemonade list

Quick question: any plans for Q4_K_M / other quants?

by MisterFynn - opened about 3 hours ago

Discussion

MisterFynn

about 3 hours ago

Hi! Really impressive work with this franken-merge. Grafting the 20 MTP layers from the unsloth Qwen3.6-35B-A3B-MTP model onto Bartowski's GGUF builds is a clever approach, and the ~20–30% inference speed gain on AMD hardware is exactly what I've been looking for. Thanks for sharing the model and the conversion script!

I noticed you currently have the IQ4_XS variant up (Kwaipilot_KAT-Coder-V2.5-Dev-IQ4_XS.bartowski.mtp.gguf). I was wondering how you've found IQ4_XS comparing to Q4_K_M in terms of quality and stability? I know IQ4_XS saves a bit of VRAM and can be slightly faster on AMD, but I've also heard Q4_K_M tends to be more consistent across different workloads.

Would you consider releasing a Q4_K_M (or even Q5_K_M) version as well? Lower-bit options would be incredibly helpful for anyone working with tighter VRAM targets, and even a couple of key variants would make a big difference for broader accessibility.

If you're open to it, I'd be happy to help test or benchmark any new quants. Either way, thanks again for pushing this forward — really appreciate the effort!

Keep up the great work!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment