Instructions to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF",
	filename="Qwen2.5-1.5B-RYS-4-7-Q4_K_M.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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with Ollama:
```
ollama run hf.co/john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
```

Unsloth Studio

How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-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 john-broadway/Qwen2.5-1.5B-RYS-4-7-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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF to start chatting

How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

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": "john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

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 john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/Qwen2.5-1.5B-RYS-4-7-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-1.5B-RYS-4-7-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-1.5B-RYS-4-7

Qwen2.5-1.5B-Instruct with layers 4-6 duplicated. A 3-layer balanced block runs twice on every forward pass.

28 base layers → 31 after duplication. No training, no merging, no weight changes.

Math +3.18. EQ +6.25 (71.37 → 77.62). Reasoning +11.76% (76.47% → 88.24%). All three metrics up.

Results

Metric	Baseline	RYS (4,7)	Delta
Math	0.5395	0.5713	+3.18
EQ	71.37	77.62	+6.25
Reasoning	76.47%	88.24%	+11.76

The balanced daily driver. Two clean circuits at this size, both inside the L4-L7 window. Duplicating this 3-layer block boosts math, EQ, and reasoning simultaneously — no trade-down anywhere. The best-all-around performer relative to size in the v1 collection.

Usage

llama-server -m Qwen2.5-1.5B-RYS-4-7-Q4_K_M.gguf -ngl 99

Full sweep data

51 configurations tested. (4,7) is the headline pick from the v1 writeup. Full sweep data in the v2 corpus dataset.

Part of the RYS Sovereign Collection v1.

Where this sits in the Sovereign Collection

v1 — Qwen2.5 cross-scale + Qwen3-32B headline. Four sizes from 0.5B to 32B; RYS works at every scale, with the lift size and dimension shifting by baseline:

0.5B → EQ specialist
1.5B → balanced daily driver
7B → math specialist via (8,12)
32B → the headline "Big Boy"

v2 — cross-architecture extension. 21 model variants across 10 architecture families. Headline: weak baselines lift more, in their weakest dimension. → john-broadway/rys-sovereign-collection-v2

Credit

John Broadway, with collaboration from Claude (Opus 4.6 in April 2026 build; Opus 4.7 in May 2026 analysis and publication). Original RYS method by David Ng on Qwen2-72B; sweep toolkit by alainnothere.