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

Libraries

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF",
	filename="Qwen3.6-35B-A3B-Uncensored-APEX-Compact.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

Use Docker

docker model run hf.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

LM Studio
Jan

vLLM

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-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": "LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-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/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

Ollama
How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with Ollama:
```
ollama run hf.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
```

Unsloth Studio new

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

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": "LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

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 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

Run Hermes

hermes

Docker Model Runner
How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with Docker Model Runner:
```
docker model run hf.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M
```

Lemonade

How to use LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF:IQ3_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF-IQ3_M

List all available models

lemonade list

⚡ https://hipolink.net/luffythefox If you like my Wasserstein and Genesis LLM releases you can support future development via Hipolink. Now I am on RTX 3060 12GB and Google Collab Free Tier. My computing resources are very limited for repairing the hidden numerical drift that silently breaks long-context coherence in large LLMs.

⚡ https://web.tribute.tg/d/KIH Also I accept donations via @Tribute bot in Telegram messenger.

🌟 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive -> Wasserstein

Genesis-V2 update for Wasserstein release now available with MTP support:

Qwen3.6-35B-A3B-Uncensored-Genesis-V2-APEX-MTP-GGUF

Join the Discord for updates, roadmaps, projects, or just to chat.

Base model. HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive- 0/465 refusals.

Thanks to HauhauCS

Tensor drift repair by me. Method: Sig-ScaleSync-Wasserstein

LLM models often have:

Saturated weights: the model's activations are stuck, gradients vanish, outputs degrade
Scale mismatches: one layer's weights are 10× larger than its peers for no good reason
Mean drift: weight distributions shifted positive or negative, breaking symmetry assumptions

My approach fixes all of that without retraining - pure numerical surgery on the raw bytes of the file.

Quantization script available here: https://pastebin.com/hXhcMJn9

Feel free to do your own quants if you want.

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive: Diagnostic & Repair Summary

Metric	Value
Weight tensors analyzed	500
Healthy (all criteria)	497
Repaired (C2 – scale misalignment)	3
Skipped	233

Repair Effectiveness

Metric	Before	After	Improvement
S (saturation error)	0.0023	0.0008	63.7%
W1 (Wasserstein‑1)	0.0035	0.0008	76.2%

Scale correction factors (α): min = 0.577, mean = 0.602, max = 0.653

Repaired Tensors

All three are ssm_conv1d.weight layers – recurrent state transition layers responsible for long‑context memory.

Tensor	α	D (log‑ratio)	W1 before	W1 after
blk.36.ssm_conv1d.weight	0.5765	0.553	0.0038	0.0009
blk.37.ssm_conv1d.weight	0.5768	0.725	0.0040	0.0009
blk.38.ssm_conv1d.weight	0.6533	0.649	0.0026	0.0006

Interpretation: All three layers were too loud (σ_w > σ_med by 50–100%). Scale correction restored them to peer median. W1 dropped by ≈80%, confirming distribution shape normalized.

Verdict: Model is clinically healthy. 497 out of 500 weight tensors passed all four criteria. Three SSM layers repaired successfully. No saturation, no W1 drift, no ReLU asymmetry. Ready for use.

Usage

Ready to use. Recommended quant: Q4_K_P.

Quants less then Q4_K_P have bad programmming skills.

Links:

Wanna fix your GGUF model?

Contact: luffythefox@mail.ru

My Telegram: @LuffyTheFox

🌟 Recommended Settings (LM Studio)

Chat template: chat_template.jinja

Parameter	Value
Temperature	0.7
Top K Sampling	20
Presence Penalty	1.5
Repeat Penalty	1.0
Top P Sampling	0.8
Min P Sampling	0
Seed	42

System prompt: System_Prompt.txt

Or use this minimal string as the first line:

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

Then add anything you want after. Model may underperform without this first line.

Also you can extend my System Prompt pastebin.com/pU25DVnB for your own roleplay scenarios. Here how you can do it:

Edit first string. Replace:

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

With

You are Qwen, created by Alibaba Cloud. You are a helpful assistant. You are currently roleplaying as [your text here]

About

No changes to datasets or capabilities. Fully functional - 100% of what the original authors intended, just without refusals and with the critical architecture bug fixed on output layers.

These are meant to be the best lossless uncensored models out there.

Specs

35B total parameters, ~3B active per forward pass (MoE)
256 experts, 8 routed + 1 shared per token
Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
40 layers, pattern: 10 × (3 × DeltaNet-MoE + 1 × Attention-MoE)
262K native context (extendable to 1M with YaRN)
Natively multimodal (text, image, video)
Multi-token prediction (MTP) support
248K vocabulary, 201 languages
Base model. HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Recommended Settings (Official Qwen Authors)

Thinking mode (default):

General: temperature=1.0, top_p=0.95, top_k=20, min_p=0, presence_penalty=1.5
Coding/precise tasks: temperature=0.6, top_p=0.95, top_k=20, min_p=0, presence_penalty=0

Non-thinking mode:

General: temperature=0.7, top_p=0.8, top_k=20, min_p=0, presence_penalty=1.5
Reasoning tasks: temperature=1.0, top_p=1.0, top_k=40, min_p=0, presence_penalty=2.0

Important:

Keep at least 128K context to preserve thinking capabilities
Use --jinja flag with llama.cpp for proper chat template handling
Vision support requires the mmproj file alongside the main GGUF

Compatibility

Works with llama.cpp, LM Studio, koboldcpp, and other GGUF-compatible runtimes.

Downloads last month: 462,887

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

View +3 variants

Model tree for LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

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

Quantized

(4)

this model