Instructions to use XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-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 XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf XpressAI/Qwen3.5-27B-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 serve -hf XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf XpressAI/Qwen3.5-27B-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/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf XpressAI/Qwen3.5-27B-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/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

Use Docker

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

LM Studio
Jan
Ollama
How to use XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF with Ollama:
```
ollama run hf.co/XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use XpressAI/Qwen3.5-27B-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 serve -hf XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-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": "XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use XpressAI/Qwen3.5-27B-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 serve -hf XpressAI/Qwen3.5-27B-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/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-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 "XpressAI/Qwen3.5-27B-RYS-UD-Q4_K_XL-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"

Add other model scores for comparison

by dottreo - opened Mar 27

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+16

-16

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -53,22 +53,22 @@ rys_30-33 shows the best combined improvement across reasoning categories. rys_3
 ## Benchmark scores
-Intial, partial benchmark results from running BFCLv4:
-| task | Accuracy |
-| :--- | :--- |
-| irrelevance | 86.67% |
-| multiple | 96.50% |
-| simple_java | 62.00% |
-| simple_javascript | 72.00% |
-| simple_python | 95.25% |
-| live_irrelevance | 82.24% |
-| live_multiple | 79.68% |
-| live_relevance | 81.25% |
-| live_simple | 84.50% |
-| multi_turn_base | 74.50% |
-| multi_turn_long_context | 67.50% |
 ---

 ## Benchmark scores
+Initial, partial benchmark results from running BFCLv4. Scores of other models from Leaderboard.
+| Task | Qwen3.5-27B-RYS-30-34 (Δ vs Best) | Claude Opus 4.5 (FC) | Claude Sonnet 4.5 (FC) | GLM 4.6 (FC) | Grok-4 (FC) | GPT-5.2 (FC) |
+|------|-----------------------------------|---------------------|-----------------------|--------------|-------------|--------------|
+| irrelevance | 86.67% (-1.25%) | 85.83% | **87.92%** | 85.42% | 77.50% | 80.00% |
+| multiple | **96.50%** | 95.50% | 95.50% | 95.00% | 92.50% | 88.00% |
+| simple_java | 62.00% (-2.00%) | 60.00% | 62.00% | **64.00%** | 62.00% | 62.00% |
+| simple_javascript | 72.00% (-2.00%) | **74.00%** | 58.00% | 64.00% | 66.00% | 64.00% |
+| simple_python | 95.25% (-2.50%) | 96.50% | **97.75%** | 94.75% | 92.50% | 92.75% |
+| live_irrelevance | 82.24% (-3.05%) | 83.60% | **85.29%** | 84.50% | 73.30% | 78.85% |
+| live_multiple | **79.68%** | 78.16% | 78.92% | 78.92% | 73.88% | 70.37% |
+| live_relevance | 81.25% (-6.25%) | 62.50% | 68.75% | 75.00% | **87.50%** | 75.00% |
+| live_simple | 84.50% (-5.03%) | 86.43% | **89.53%** | **89.53%** | 82.17% | 71.71% |
+| multi_turn_base | 74.50% (-6.50%) | **81.00%** | 69.00% | 74.50% | 44.00% | 36.50% |
+| multi_turn_long_context | 67.50% (-3.00%) | **70.50%** | 59.00% | 66.50% | 44.00% | 30.50% |
 ---