Instructions to use unsloth/Qwen3.5-35B-A3B-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 unsloth/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.5-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.5-35B-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/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Qwen3.5-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Qwen3.5-35B-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/Qwen3.5-35B-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/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF to start chatting

How to use unsloth/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF:UD-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": "unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3.5-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3.5-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-35B-A3B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF:UD-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 unsloth/Qwen3.5-35B-A3B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/Qwen3.5-35B-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/Qwen3.5-35B-A3B-GGUF:UD-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 "unsloth/Qwen3.5-35B-A3B-GGUF:UD-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 discussion

Resources

View closed (4)

Mar 5 - 'Final' Update: iMatrix + Benchmarks + New quant algo

pinned

❤️🚀 7

#31 opened 6 months ago by

danielhanchen

Feb 27: GGUF Update + Tool-calling fixes + Benchmarks

pinned

🚀🔥 12

#10 opened 6 months ago by

danielhanchen

Question for @unsloth: mobile deployment?

#46 opened 2 months ago by

3morixd

Getting ///////// output with this model across all quants

#45 opened 5 months ago by

dmcleod97

Why this model refuses to provide surgery procedure?

#44 opened 5 months ago by

JLouisBiz

Has anyone finally gotten this model to work properly or are we still waiting for another update?

#42 opened 5 months ago by

systems-u

Telemetry tips for Claude code with Qwen

🔥❤️ 2

#41 opened 5 months ago by

tstello

New to all things HF and AI, but bugs I am familiar with. ROCm: illegal memory access. Model: Qwen3.5-35B-A3B-Q4_K_M

#40 opened 5 months ago by

jwallgood

Is there a way to enable/disable thinking at the request level?

#39 opened 6 months ago by

septerium

why qwen3.5 think so long？

#38 opened 6 months ago by

sysy007uuu2

What happened to Qwen3.5-35B-A3B-UD-Q4_K_M.gguf ?

👍 1

#37 opened 6 months ago by

martinsky

Fix Jinja Template: Add support for multiple System messages and Add Support for Developer messages

#36 opened 6 months ago by

muoikai

Usage for image description

#35 opened 6 months ago by

hamster007

Fix Jinja Template: Add support for multiple System messages and Add Support for Developer messages

👍 2

#34 opened 6 months ago by

q177

Is docs page down?

#33 opened 6 months ago by

Glee951

Quick question for the team about Q8_K_XL

👀 4

#30 opened 6 months ago by

jswiftie

Multimodal not detecting in LM Studio

#29 opened 6 months ago by

teddyspaghetti

Verbose looping

#28 opened 6 months ago by

islameissa

Bug: Model does not produce <think></think> tokens when enable_thinking=true

#26 opened 6 months ago by

mohamedemam

March 3, 2026 updates ?

#25 opened 6 months ago by

BitBuilder

Why did the Qwen3.5 model I used experience an automatic exit during loading?

#24 opened 6 months ago by

yangfan19910901

Still some tool calling issues

➕ 2

#22 opened 6 months ago by

LadyJun

Reasoning breaks at middle of no where

#21 opened 6 months ago by

jackson145258116

Is Image supported in this model?

#20 opened 6 months ago by

sanjilover

Endless looping while analyzing image and thinking.

➕ 1

#19 opened 6 months ago by

0707intel

LM Studio does not support the newly updated chat template

#18 opened 6 months ago by

FORNAX20

How to use Qwen3.5 GGUF in transformers?

#17 opened 6 months ago by

Jackson404

Is Q8_0 gone?

#16 opened 6 months ago by

PhilippeEiffel

Vllm support

#15 opened 6 months ago by

deece

Qwen3.5-35B-A3B-GGUF:UD-Q4_K_M does not work in Ollama 0.17.4

#14 opened 6 months ago by

Arete7

Suggestion: Preserve ssm_alpha and ssm_beta in BF16 for Q8_0 Quants (Fix for Long-Context Degradation)

👍 1

#13 opened 6 months ago by

wize-1

hello

#12 opened 6 months ago by

Vyn25

Add support for developer role in chat template (Codex compatibility)

🔥 5

#9 opened 6 months ago by

xangma

hi llama.cpp had a new optimize for qwen3.5moe. commit id:b68d751

👍 7

#8 opened 6 months ago by

Simon716

Is there some helpful regex to offload all MoE layers to the CPU?

#7 opened 6 months ago by

hdnh2006

TQ1 quant?

👍 2

#6 opened 6 months ago by

sergeysi

Update: Should now be Fixed - Bug in UD-Q4_K_XL recipe using MXFP4 for attn tensors and experts?

👍 8

#5 opened 6 months ago by

ubergarm

Prompt cache not working correctly

👀👍 6

#4 opened 6 months ago by

guiopen

Coding parameters used for Goose and Zed

#3 opened 6 months ago by

dugrema

llama cpp Error: Unknown (built-in) filter 'items' for type String

#2 opened 6 months ago by

fullstack

Benchmarks

👍 6

#1 opened 6 months ago by

coder543