Instructions to use unsloth/Qwen3.5-27B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Qwen3.5-27B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3.5-27B-GGUF",
	filename="BF16/Qwen3.5-27B-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/Qwen3.5-27B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3.5-27B-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/Qwen3.5-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3.5-27B-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/Qwen3.5-27B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3.5-27B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3.5-27B-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/Qwen3.5-27B-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/Qwen3.5-27B-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Qwen3.5-27B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Qwen3.5-27B-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/Qwen3.5-27B-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/Qwen3.5-27B-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/Qwen3.5-27B-GGUF to start chatting

How to use unsloth/Qwen3.5-27B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL

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/Qwen3.5-27B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3.5-27B-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 unsloth/Qwen3.5-27B-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/Qwen3.5-27B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use unsloth/Qwen3.5-27B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3.5-27B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.5-27B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-27B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

New discussion

Resources

View closed (7)

Mar 5 Update: New iMatrix + Variants

pinned

❤️ 6

#20 opened 3 months ago by

danielhanchen

context processing always repeats

#29 opened about 2 months ago by

blallo27

turn out not only Caude Code, OpenCode also very easily trigger infinite '///' Qwen3.5-27B

#28 opened 2 months ago by

rosspanda0

Tool calling is broken when thinking is enabled, at least with UD-Q4_K_XL quants

👀 1

#27 opened 3 months ago by

Juodumas

Comparison to steampunque hybrid quant

#26 opened 3 months ago by

Throghar

27B GGUF quants benchmark?

👀 1

#25 opened 3 months ago by

rtzurtz

Instruction following and infinite loop

#24 opened 3 months ago by

saipubw

Could you create a Qwen3.5-27B-UD-Q4_K_L or UD-Q4_K_M version that fits within 16GB VRAM?

#23 opened 3 months ago by

YuunaPhos

when new updated version waiting

👀👍 3

#22 opened 3 months ago by

gopi87

[SOLVED] llama_model_load: unknown model architecture: 'qwen35'

#21 opened 3 months ago by

drraug

qwen3.5 27b bf16 question

#19 opened 3 months ago by

OldMan12345

Hmm. Super slow performance on newest llama.cpp

#15 opened 3 months ago by

jeffwadsworth

Update status for Qwen3.5 122B and 27B GGUFs?

👍👀 23

#13 opened 4 months ago by

Chlheng

WHY qwen35 as the architecture name?

#12 opened 4 months ago by

kouji

Not supported on llama.cpp

#11 opened 4 months ago by

RealBiggly

memory error when loading 27b model on 20gb vram gpu

#10 opened 4 months ago by

selmee

LM studio error

👀 1

#9 opened 4 months ago by

rakhilml

could you create a ud q_2_k_xl?

🔥👀 5

#6 opened 4 months ago by

drmcbride

OLLAMA version

👍 3

#5 opened 4 months ago by

d4rksou1

Qwen3.5-27B still thinking even with enable_thinking false, here is the method for now to actually disable Thinking Mode on Qwen3.5-27B (llama.cpp b8148）

👀👍 5

#4 opened 4 months ago by

gannima

Q3_K_XL?

👍 2

#2 opened 4 months ago by

floory