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

Libraries

How to use unsloth/Qwen3.6-35B-A3B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="unsloth/Qwen3.6-35B-A3B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Qwen3.6-35B-A3B-GGUF", device_map="auto")

llama-cpp-python

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3.6-35B-A3B-GGUF",
	filename="BF16/Qwen3.6-35B-A3B-BF16-00001-of-00002.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 unsloth/Qwen3.6-35B-A3B-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 unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-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 unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-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 unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.6-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.6-35B-A3B-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": "unsloth/Qwen3.6-35B-A3B-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/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

SGLang

How to use unsloth/Qwen3.6-35B-A3B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/Qwen3.6-35B-A3B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3.6-35B-A3B-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/Qwen3.6-35B-A3B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3.6-35B-A3B-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use unsloth/Qwen3.6-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
```

Unsloth Studio

How to use unsloth/Qwen3.6-35B-A3B-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 unsloth/Qwen3.6-35B-A3B-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 unsloth/Qwen3.6-35B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use unsloth/Qwen3.6-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-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": "unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3.6-35B-A3B-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 unsloth/Qwen3.6-35B-A3B-GGUF:UD-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 unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use unsloth/Qwen3.6-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-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 "unsloth/Qwen3.6-35B-A3B-GGUF:UD-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 unsloth/Qwen3.6-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
```

Lemonade

How to use unsloth/Qwen3.6-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-GGUF-UD-Q4_K_M

List all available models

lemonade list

Qwen 3.6 is much slower than Qwen 3.5 for the same quatization: UD-Q4_K_XL

by adr-insc - opened Apr 17

Discussion

adr-insc

Apr 17

Has anybody else experienced this? For the same task (analyzing a feature) Qwen 3.5 finishes in under 1 minute while Qwen 3.6 crunches tens of minutes not finishing.

danielhanchen

Unsloth AI org Apr 17

Has anybody else experienced this? For the same task (analyzing a feature) Qwen 3.5 finishes in under 1 minute while Qwen 3.6 crunches tens of minutes not finishing.

Q4_K_XL is now bigger so it might not fit in your device, try a smaller quant and compare

adr-insc

Apr 17

Q4_K_XL is now bigger so it might not fit in your device, try a smaller quant and compare

Actually, I've tried with UD-Q2_K_XL as well, and it was still slower. However, it wasn't a RAM/VRAM issue. 3.6 used the same resources as 3.5. I use it with llama-server, with these args:

    .arg("-cmoe") 
    .arg("--ctx-size")
    .arg("24000") 
    .arg("-n")
    .arg("20000")
    .arg("--temp")
    .arg("0.6")
    .arg("--top-p")
    .arg("0.95")
    .arg("--top-k")
    .arg("20")
    .arg("-ngl")
    .arg("45")
    .arg("-fa")
    .arg("on")
    .arg("--jinja")

Lex-N

Apr 17

•

edited Apr 17

...However, it wasn't a RAM/VRAM issue.

What hardware resources do you use, and on what comparable task could we benchmark the models?

adr-insc

Apr 17

What hardware resources do you use, and on what comparable task could we benchmark the models?

My system is quite modest: Laptop Dell Precision 5530, Intel Core i7 8850H 2.6 GHz up to 4.3 GHz, nVidia Quadro P1000 4 GB GDDR5

The use case is for a coding agent. An example task: Test a "web access" tool just implemented ( basically a http client tool ). Qwen 3.5 did it in under 2 minutes, while Qwen 3.6 variants crunched more than 20 minutes without finishing. They ran with the same resources/parameters, as in my previous post.
Thank you.

zdjun1984

Apr 18

I had this problem too.Qwen3.6-35B-A3B-Q4_K_XL is even slower than Qwen3.5-122B-A10B-IQ4_XS,got only 5tokens/s,it seems like a Dense Model.But I got more than 30tokens/s with Qwen3.5-35B-A3B-Q4_K_XL.

zdjun1984

Apr 18

I had this problem too.Qwen3.6-35B-A3B-Q4_K_XL is even slower than Qwen3.5-122B-A10B-IQ4_XS,got only 5tokens/s,it seems like a Dense Model.But I got more than 30tokens/s with Qwen3.5-35B-A3B-Q4_K_XL.

I have updated my llama.cpp,then it got 35tokens/s.My mistake.

cryptkat

Apr 18

UD-Q4_K_XL is extremely fast on RTX5090 - Over 200 tok/s

adr-insc

Apr 18

I have updated my llama.cpp,then it got 35tokens/s.My mistake.

You mean you installed a new version of llama.cpp?

adr-insc

Apr 19

If anyone encounters the same problem, I solved it by adding --reasoning-budget 1000 to llama-server args.
The problem was not that Qwen 3.6 was slower than Qwen 3.5 at token/seconds generation. It was slower solving the task, It kept thinking and thinking without actually solving it.
Capping the reasoning budget made it much more responsive - usable, actually.

owao

Apr 22

I personally wouldn't set a thinking budget for this model :/ But in case you did so because generation speed was too slow, I discovered quite recently how llama.cpp was handling MOE models, here are some tips to get higher throughput and aiming higher quants by letting llama.cpp doing its auto-optimization: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/discussions/37#69e551731f2a0505a679d501
Hope this will help some users!

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