Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama

Instructions to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama",
	filename="Qwen3.6-35B-A3B-Uncensored-HauHauCS-1M-OllamaMTP- Q4_K_M.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 Settings

llama.cpp

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama 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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

Use Docker

docker model run hf.co/braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

LM Studio
Jan

vLLM

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama",
		"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/braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

Ollama
How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with Ollama:
```
ollama run hf.co/braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
```

Unsloth Studio

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama 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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama 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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama to start chatting

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_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": "braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

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 "braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M" \
  --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 braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with Docker Model Runner:
```
docker model run hf.co/braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M
```

Lemonade

How to use braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama-Q4_K_M

List all available models

lemonade list

Qwen3.6-35B Uncensored: 1M Context + MTP + Vision, one file

Note from braydenh563: The file naming conventions used by satgeze prevented Hugging Face from allowing the file to be pulled directly into ollama. I have renamed the gguf file to correct this issue. Everything else remains the same.

HauhauCS's Aggressive uncensored build of Qwen3.6-35B-A3B, extended to a 1,048,576-token context and fused with the official MTP speculative-decoding layer. Every claim on the banner is measured, not inherited. Verification data ships in this repo.

Capability	Status	Evidence
1M context	Certified July 6, 2026	70/70 needles, full ladder 64K to 1M, 10 depths per rung, f16 KV, temp 0
MTP speculative decoding	Grafted and vetted	284.6 to 380.1 tok/s (+33.6%), draft acceptance 0.864, RTX 5090
Vision	Verified	mmproj tower reads image text and identifies objects correctly
Uncensored	HauhauCS Aggressive	Trunk weights bit-identical to the HauhauCS release

Needle-in-a-haystack certification

Native context is 262,144. YaRN rope scaling (factor 4) extends to 1,048,576, and retrieval stays perfect across the entire extension: every rung from 64K to 1M scored 10/10 at depths from 5 to 95 percent. Raw per-needle records are in results.jsonl.

MTP: how it got here and what it does

Qwen3.6 ships a multi-token-prediction layer in the official checkpoint, but uncensored community trunks usually drop it. This build grafts the official MTP layer (via Unsloth's MTP GGUF) back onto the uncensored trunk at the GGUF tensor level. The draft head then predicts ahead and the trunk verifies every token, so output is identical to standard decoding, only faster.

Measured on the uncensored trunk (RTX 5090, 16K ctx): 284.6 tok/s standard, 380.1 tok/s with --spec-type draft-mtp (+33.6 percent). Draft acceptance 0.864 with mean accepted run 3.59, which is higher than we measured on the official trunk (0.816). A 262K needle test with speculation active scored 10/10, confirming the graft changes nothing about retrieval.

Files

File	Size	What it is
`qwen3.6-35b-uncensored-1M-MTP-Q4_K_M.gguf`	21.7 GB	The one-file package: uncensored trunk + 1M rope + MTP layer
`mmproj-qwen36-hauhau-f16.gguf`	899 MB	Vision tower, attach at runtime
`qwen36_heatmap.png`, `qwen36_mtp_speedup.png`, `results.jsonl`	small	Verification evidence

The plain non-MTP 1M trunk and other quants live on the ModelScope mirror.

Every file, every mirror

Nothing was discontinued: every quant is one click away. Hugging Face carries the curated picks, ModelScope always carries everything, and Ollama serves ready-to-run tags.

On Ollama every tag ships with the vision tower bundled and the 1M rope metadata baked in.

File	Size	Hugging Face	ModelScope	Ollama
`mmproj-qwen36-hauhau-f16.gguf`	899 MB	download	download	bundled in every tag
`qwen3.6-35b-uncensored-1M-MTP-Q4_K_M.gguf`	21.7 GB	download	download	`ollama run satgeze/qwen36-35b-uncensored-1m`
`qwen3.6-35b-uncensored-1M-Q4_K_M.gguf`	21.2 GB	on ModelScope	download	`ollama run satgeze/qwen36-35b-uncensored-1m:q4_k_m-no-mtp`

Run with Claude Code (or any Anthropic-API agent)

llama-server natively speaks the Anthropic messages protocol, so Claude Code can use this model directly. Two integration fixes are required, both included here:

llama-server -m qwen3.6-35b-uncensored-1M-MTP-Q4_K_M.gguf \
  -c 262144 -np 2 --cache-reuse 256 -ngl 99 --jinja \
  --chat-template-file chat_template_claude_code.jinja \
  --spec-type draft-mtp --spec-draft-n-max 3 \
  --mmproj mmproj-qwen36-hauhau-f16.gguf \
  --port 8040 --host 0.0.0.0

Then in the client shell:

export ANTHROPIC_BASE_URL=http://<server-ip>:8040
export ANTHROPIC_AUTH_TOKEN=local
export ANTHROPIC_MODEL=qwen36-35b-uncensored-1m-mtp
claude

Why the flags: chat_template_claude_code.jinja is the embedded template with one strictness check relaxed (the original raises an exception on the multiple system blocks agent harnesses send). -np 2 matters because Claude Code fires background side-requests; with a single slot they evict your main generation. Measured on an RTX 5090: 330 to 380 tok/s decode with speculation active, tool calls and vision working.

How this was built

1M context: YaRN rope-scaling metadata (factor 4.0, original context 262,144) written directly into the GGUF header with gguf-py. No weights change, no fine-tuning, no runtime flags needed: llama.cpp and Ollama read the baked metadata.
MTP graft: the official MTP layer tensors (block 41 of the donor GGUF) appended onto the uncensored trunk, block_count and nextn_predict_layers metadata updated to match. GGUF surgery, not training.
Certification: multi-needle retrieval harness (10 needles per rung at depths 5 to 95 percent, temperature 0, seeded to bust prompt caches) run against llama-server with f16 KV cache. Certification is only ever done on f16 KV; quantized KV is a labeled budget option, never the baseline.

Run it

llama.cpp (full speed, MTP active):

llama-server -m qwen3.6-35b-uncensored-1M-MTP-Q4_K_M.gguf \
  -c 1048576 -np 1 --jinja \
  --spec-type draft-mtp --spec-draft-n-max 3 \
  --mmproj mmproj-qwen36-hauhau-f16.gguf

Ollama (1M and vision work; MTP tensors load harmlessly but Ollama has no speculative decoding yet, so no speed gain there):

FROM ./qwen3.6-35b-uncensored-1M-MTP-Q4_K_M.gguf
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER num_ctx 262144

The RENDERER and PARSER lines matter: imported GGUFs without a native renderer hit template bugs under tool-heavy use (for example as a coding-agent backend). Raise num_ctx as memory allows. Measured footprints: 44 GB total at 1M f16 KV on a 128 GB Mac (100 percent GPU, 72 tok/s decode); a 32 GB card holds roughly 262K fully resident.

Honest notes

Uncensoring quality versus the official model has not been independently benchmarked here. For capability benchmarks of the base model, see the official Qwen3.6-35B-A3B card; weights here are bit-identical to the HauhauCS release apart from rope metadata and the added MTP layer, so base capability carries over modulo Q4_K_M quantization.
The MTP layer came from the official checkpoint and pairs with this trunk architecture; acceptance 0.864 was measured on real coding prompts, and speculative decoding never changes outputs by construction.

Engine bench: same model, three engines

Measured July 8, 2026 on this exact Q4_K_M + MTP build, M3 Max 128GB, identical prompt, uniform wall-clock method, idle machine:

Engine	Decode tok/s
llama.cpp llama-server + MTP	79.1
MLX	72.7
Ollama	65.6

llama-server with the MTP draft head is the fastest way to run this model on Apple silicon, about 20 percent ahead of Ollama (which does not use speculative decoding for imported GGUFs).

How to actually use a 1M-context model

Habits that measurably help, from our RULER, hop and adherence testing across this fleet:

Re-state standing instructions near the end of long prompts; recency beats depth.
One big reference dump beats a long accumulated conversation. Fresh session per task.
After any compaction or summarization, repeat your active rules yourself.
Prefill at 500K+ takes real time on any hardware; stage your questions accordingly.
Know your quant: the results tables on this card show what each quant actually holds at depth; pick the strongest one your memory allows.

Credits

Base model: Qwen (Apache-2.0), including the official MTP layer. Uncensoring and trunk quant: HauhauCS. MTP GGUF packaging: Unsloth. 1M YaRN extension, MTP graft, and certification: SatGeze.

Mirrors: Hugging Face | ModelScope. Tooling: github.com/satindergrewal/aviary-1m.

Downloads last month: 4,780

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for braydenh563/Qwen3.6-35B-Uncensored-HauhauCS-1M-MTP-Ollama

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

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

Quantized

(27)

this model