Instructions to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF",
	filename="Qwen3.5-0.8B-rys_4-11-UD-Q4_K_XL.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with Ollama:
```
ollama run hf.co/XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF to start chatting

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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": "XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with Docker Model Runner:
```
docker model run hf.co/XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
```

Lemonade

How to use XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XpressAI/Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.5-0.8B-RYS-UD-Q4_K_XL-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Qwen3.5-0.8B — RYS Layer Surgery (GGUF)

A modified version of Qwen3.5-0.8B-Instruct produced by RYS layer duplication — no training, no weight changes, just routing hidden states through a specific circuit twice.

Based on David Ng's RYS method.

Files

File	Layers	Size
`Qwen3.5-0.8B-UD-Q4_K_XL.gguf`	24	533 MiB
`Qwen3.5-0.8B-rys_4-11-UD-Q4_K_XL.gguf`	32	621 MiB

Probe scores

Scores from an internal sweep benchmark run during circuit search. Sample sizes are small — treat these as directional indicators, not definitive benchmarks.

Model	Math	EQ	Reasoning
Base (24 layers)	0.062	0.0	0.000
rys_4-11 (32 layers)	0.000	36.3	0.353

Math: Ng's partial-credit scoring on a small GSM8K sample
EQ: EQ-Bench-style emotional intelligence score (0–100)
Reasoning: fraction correct across causal, date, logic, navigation, and GSM8K probes

Note: the math score drops to 0 in the RYS model. The base model's math score (0.062) is already very low for a 0.8B model.

What is RYS?

Transformers self-organise during training into functional circuits — contiguous blocks of layers that act together. The RYS technique duplicates a specific block in the forward pass using the same weights, with no extra copies on disk beyond the GGUF file overhead:

Normal:   0 → 1 → … → 3 → 4 → 5 → 6 → 7 → 8 → 9 → 10 → 11 → 12 → … → 23
rys_4-11: 0 → 1 → … → 3 → 4 → 5 → 6 → 7 → 8 → 9 → 10 → 11
                           → 4 → 5 → 6 → 7 → 8 → 9 → 10 → 11 → 12 → … → 23

The model processes the circuit twice, without any weight changes or fine-tuning.

Hybrid Mamba/attention architecture constraint

Qwen3.5-0.8B is a hybrid SSM/attention model (full_attention_interval = 4): full attention every 4th layer, Gated DeltaNet SSM everywhere else. The architecture repeats 6 times:

3 × (DeltaNet → FFN) → 1 × (Attention → FFN)

This creates a hard constraint on layer surgery: the total layer count must remain divisible by 4.

Block size 4 → 24 + 4 = 28 layers (28 ÷ 4 = 7 ✓)
Block size 8 → 24 + 8 = 32 layers (32 ÷ 4 = 8 ✓)
Block size 3 → 24 + 3 = 27 layers (27 ÷ 4 = 6.75 ✗ → crash)

The winning circuit (layers 4–11) spans exactly two complete SSM+Attention units, which appear to form a coherent functional block. No 4-layer sub-block within this range produced comparable improvements in the fine-grained sweep.

How the circuit was found

A two-pass sweep over the 24-layer model:

Pass 1 — 8-layer blocks, stride 4, layers 0–16:

(4, 12) dominant: EQ=36.3, reasoning=0.353 vs baseline EQ=0.0, reasoning=0.0

Pass 2 — 4-layer blocks, stride 1, layers 4–16:

No 4-layer sub-block matched the 8-layer result
Best 4-layer blocks: (11,15) reasoning=0.235, (7,11) EQ=4.73

The 8-layer block is the minimum effective circuit size for this model.

Usage

llama.cpp / llama-server

llama-server -m Qwen3.5-0.8B-rys_4-11.gguf -ngl 99 --port 8080

Thinking mode

Qwen3.5 defaults to thinking mode (<think>…</think>). Add /no_think to the system prompt for fast, direct answers:

messages = [
    {"role": "system", "content": "/no_think"},
    {"role": "user",   "content": "Your question here"}
]

VRAM requirements

The model weights are ~621 MiB. Runs on any modern GPU or CPU.

Credits

David Ng for the original RYS method
Unsloth for the base Q4_K_XL GGUF quantization
Qwen team for Qwen3.5-0.8B
llama.cpp for local inference

License

Apache 2.0 (inherited from base model)

Downloads last month: 6

GGUF

Model size

0.9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support