Instructions to use YTan2000/Qwen3.5-27B-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YTan2000/Qwen3.5-27B-TQ3_4S 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 YTan2000/Qwen3.5-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.5-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
./llama-cli -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.5-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

Use Docker

docker model run hf.co/YTan2000/Qwen3.5-27B-TQ3_4S:BF16

LM Studio
Jan

vLLM

How to use YTan2000/Qwen3.5-27B-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YTan2000/Qwen3.5-27B-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YTan2000/Qwen3.5-27B-TQ3_4S",
		"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/YTan2000/Qwen3.5-27B-TQ3_4S:BF16

Ollama
How to use YTan2000/Qwen3.5-27B-TQ3_4S with Ollama:
```
ollama run hf.co/YTan2000/Qwen3.5-27B-TQ3_4S:BF16
```

Unsloth Studio

How to use YTan2000/Qwen3.5-27B-TQ3_4S 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 YTan2000/Qwen3.5-27B-TQ3_4S 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 YTan2000/Qwen3.5-27B-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for YTan2000/Qwen3.5-27B-TQ3_4S to start chatting

How to use YTan2000/Qwen3.5-27B-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

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": "YTan2000/Qwen3.5-27B-TQ3_4S:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use YTan2000/Qwen3.5-27B-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.5-27B-TQ3_4S:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use YTan2000/Qwen3.5-27B-TQ3_4S with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.5-27B-TQ3_4S:BF16

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 "YTan2000/Qwen3.5-27B-TQ3_4S:BF16" \
  --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 YTan2000/Qwen3.5-27B-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/YTan2000/Qwen3.5-27B-TQ3_4S:BF16
```

Lemonade

How to use YTan2000/Qwen3.5-27B-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YTan2000/Qwen3.5-27B-TQ3_4S:BF16

Run and chat with the model

lemonade run user.Qwen3.5-27B-TQ3_4S-BF16

List all available models

lemonade list

Qwen3.5-27B-TQ3_4S

Clean base TQ3_4S GGUF release for Qwen3.5-27B.

TQ3_4S is a 3.5-bit Walsh-Hadamard-transform weight format with four per-8 scales per 32-weight block.

Summary

Format: TQ3_4S
Model size: about 12.9 GiB
Target runtime: public TurboQuant-enabled llama.cpp
Intended use: local inference on consumer GPUs
Multimodal projector included: mmproj-BF16.gguf

Quality

Qwen3.5-27B, wiki.test.raw, c=2048:

Format	PPL	Size
`TQ3_4S`	`6.8224 +/- 0.04534`	`12.9 GiB`
`Q3_K_S`	`6.8630 +/- 0.04583`	`11.4 GiB`
`TQ3_1S`	`6.9807 +/- 0.04690`	`12.9 GiB`
`EXL3 3.0bpw`	`7.027580`	`~13.0 GiB`

Notes:

TQ3_4S and Q3_K_S are full-pass llama-perplexity results.
TQ3_1S is also a full-pass llama-perplexity result at c=2048.
EXL3 3.0bpw is from a local 145 x 2048 eval, not llama-perplexity.
This 27B result should not be read as evidence that plain TQ3_4S works equally well on smaller dense models.

Runtime

This model requires the public TurboQuant runtime fork:

https://github.com/turbo-tan/llama.cpp-tq3
LM Studio setup: docs/backend/LMStudio.md

Build and run:

git clone https://github.com/turbo-tan/llama.cpp-tq3.git
cd llama.cpp-tq3

cmake -B build -DGGML_CUDA=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build -j

./build/bin/llama-server \
  -m /path/to/Qwen_Qwen3.5-27B-TQ3_4S.gguf \
  -ngl 99 \
  -fa on \
  -c 8192 \
  -ctk q8_0 -ctv q8_0 \
  --cache-ram 0 \
  --no-warmup --jinja \
  --reasoning off --reasoning-budget 0 --reasoning-format deepseek \
  --port 8090

Vision / Image Input

Use the included projector:

./build/bin/llama-server \
  -m /path/to/Qwen_Qwen3.5-27B-TQ3_4S.gguf \
  -mm /path/to/mmproj-BF16.gguf \
  -ngl 99 -c 8192 -np 1 \
  -ctk q8_0 -ctv q8_0 -fa on \
  --cache-ram 0 --no-warmup --jinja \
  --reasoning off --reasoning-budget 0 --reasoning-format deepseek \
  --no-mmproj-offload

If your frontend says image input is unsupported, it is usually still pointed at a server instance that was started without --mmproj.

Notes

This upload is the clean base TQ3_4S release, not the private KLD-guided mixed-precision variants.

Credits

llama.cpp
Qwen3.5-27B
Walsh-Hadamard / transform-quantization line including RaBitQ, TurboQuant, and related work

Downloads last month: 165

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for YTan2000/Qwen3.5-27B-TQ3_4S

Base model

Qwen/Qwen3.5-27B

Quantized

(224)

this model

Collection including YTan2000/Qwen3.5-27B-TQ3_4S

Qwen 3.5

Collection

Collection for Qwen3.5 models • 6 items • Updated May 23