Instructions to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

LM Studio
Jan

vLLM

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

Ollama
How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with Ollama:
```
ollama run hf.co/SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
```

Unsloth Studio

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF to start chatting

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

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": "SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL
```

Lemonade

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-heretic-MTP-GGUF-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

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 SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL

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 "SassyDiffusion/Qwen3.6-35B-A3B-heretic-MTP-GGUF:Q4_K_XL" \
  --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"

New version?

by AI-Joe-git - opened May 12

Discussion

AI-Joe-git

May 12

Hello thanks for sharing this 😁

Is this working now no more missing layer?

SassyDiffusion

Owner May 12

•

edited May 12

Hello thanks for sharing this 😁

Is this working now no more missing layer?

Q8_K_KL is working for me with the latest mtp-clean branch.

Got ~19 t/s boost (64 -> 83) with MTP on my machine for this model.

SassyDiffusion

Owner May 14

•

edited May 14

The current latest mtp-clean branch seems to be broken atm. The latest working commit in the branch that works for me is https://github.com/ggml-org/llama.cpp/commit/e7b4848151377395b1693d326d1cda3fcd61c2d9.

zzxc3c

May 17

Will there be new version with master llama.cpp now that it's been merged?

SassyDiffusion

Owner May 17

Will there be new version with master llama.cpp now that it's been merged?

@zzxc3c I don't think a new quant is needed.

arzeth

May 17

I've just tried Qwen3.6-35B-A3B-heretic.EMB_BF16.Q8_K_XL.gguf,
and it works on llama.cpp b9189 (2026-05-16) 😀

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