Instructions to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp",
	filename="hauhau_qwen36_35b_a3b_mxfp4_mtp.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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
# Run inference directly in the terminal:
llama cli -hf robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
# Run inference directly in the terminal:
llama cli -hf robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
# Run inference directly in the terminal:
./llama-cli -hf robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
# Run inference directly in the terminal:
./build/bin/llama-cli -hf robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Use Docker

docker model run hf.co/robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

LM Studio
Jan

vLLM

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Ollama
How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with Ollama:
```
ollama run hf.co/robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
```

Unsloth Studio

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp to start chatting

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

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": "robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

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 "robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp" \
  --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 robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with Docker Model Runner:
```
docker model run hf.co/robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp
```

Lemonade

How to use robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Run and chat with the model

lemonade run user.hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp-{{QUANT_TAG}}

List all available models

lemonade list

hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

This repo contains a local MXFP4_MOE GGUF export of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive together with a separate MTP draft GGUF for speculative decoding in a patched local llama.cpp toolchain.

Files

hauhau_qwen36_35b_a3b_mxfp4_robinstyle.gguf: main text model in robinshao-style MXFP4 layout
hauhau_qwen36_35b_a3b_mxfp4_mtp.gguf: MTP draft GGUF used with --spec-type draft-mtp
llama.cpp.src-patched.zip: patched local llama.cpp source snapshot used for conversion and serving
build_result.json: build and validation summary for the main model and MTP draft
mtp-benchmark.json: short local speed comparison between baseline and MTP serving

Quantization Notes

Source FP16 weights: khoi11/Qwen3.6-35B-A3B-Uncensored-HauhauCS-FP16
Upstream model lineage: HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Main model converted for text inference and quantized into a robinshao-style MXFP4_MOE GGUF
MTP draft exported as a separate GGUF for speculative decoding with patched llama.cpp
Vision tensors are not included in the final serving package

Local Deployment Notes

This pair was validated locally on Windows with patched llama.cpp using speculative decoding:

llama-server -m hauhau_qwen36_35b_a3b_mxfp4_robinstyle.gguf \
  --spec-type draft-mtp \
  --spec-draft-model hauhau_qwen36_35b_a3b_mxfp4_mtp.gguf \
  --spec-draft-device CUDA0 \
  --spec-draft-ngl all \
  --jinja \
  --device CUDA0 \
  --gpu-layers all \
  --ctx-size 8192 \
  --batch-size 768 \
  --ubatch-size 128 \
  --flash-attn on \
  --cache-type-k f16 \
  --cache-type-v f16 \
  --cache-ram 0

In a short local API benchmark on an RTX 4000 Ada, the MTP setup improved decode speed from about 103.45 tok/s to about 131.65 tok/s, roughly 1.27x.

Caveats

This is a text-only export, not the original multimodal package.
The draft file is intended for speculative decoding and is not a standalone replacement for the main model.
Native training context metadata remains 262144, but the actual no-offload local limit depends on GPU VRAM, KV cache settings, and whether the draft model is loaded.

Downloads last month: 94

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for robinshao/hauhau_qwen36_35b_a3b_mxfp4_gguf_mtp

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Quantized

(29)

this model