Instructions to use john-broadway/Qwen3-8B-RYS-16-19-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/Qwen3-8B-RYS-16-19-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="john-broadway/Qwen3-8B-RYS-16-19-GGUF",
	filename="Qwen3-8B-RYS-16-19-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

llama.cpp

How to use john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/Qwen3-8B-RYS-16-19-GGUF with Ollama:
```
ollama run hf.co/john-broadway/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
```

Unsloth Studio new

How to use john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF to start chatting

Pi new

How to use john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use john-broadway/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-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/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use john-broadway/Qwen3-8B-RYS-16-19-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/Qwen3-8B-RYS-16-19-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/Qwen3-8B-RYS-16-19-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-8B-RYS-16-19-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3-8B-RYS-16-19

RYS-enhanced Qwen3-8B with layers 16-19 duplicated. 36 layers expanded to 39. Zero training, zero weight changes.

Math +6.7%, Reasoning +23.5%. Baseline reasoning healed from 53% to 76%.

Results

Metric	Baseline	RYS (16,19)	Delta
Math	0.6568	0.7240	+6.7%
EQ	91.91	90.74	-1.17
Reasoning	52.94%	76.47%	+23.5%

117 configurations tested. The 8B's baseline reasoning was the weakest in the Qwen3 family (53%). RYS at (16,19) heals it to 76%.

Usage

llama-server -m Qwen3-8B-RYS-16-19-Q4_K_M.gguf -ngl 99

Full sweep data

117 configurations tested. Sweep results published with the model files.

Part of the v2 Qwen3-family cohort — parallel Qwen3-family RYS-applied weights from April 2026, expanded alongside the v1 Qwen2.5 cross-scale collection. (The "four model scales" originally referenced here was a Qwen3-only expansion; the original v1 writeup described Qwen2.5 cross-scale + Qwen3-32B as headline.)

Where this sits in the Sovereign Collection

v1 — Qwen2.5 cross-scale + Qwen3-32B headline crossover (the original v1 intent per the 2026-04-11 writeup). 5 model repos on HuggingFace; see john-broadway.

v2 Qwen3-family cohort (this card's cohort — parallel Qwen3-family RYS-applied weights, April 2026):

0.6B — john-broadway/Qwen3-0.6B-RYS-10-13-GGUF
1.7B — john-broadway/Qwen3-1.7B-RYS-7-10-GGUF
8B (this card) — john-broadway/Qwen3-8B-RYS-16-19-GGUF

v2 cross-architecture corpus (21 model variants spanning 10 architecture families): john-broadway/rys-sovereign-collection-v2

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

v2 cross-architecture context (2026-05-13)

This model's place in the v2 curve: baseline reasoning 52.94%, peak RYS Δ +29.41%. Of 117 swept configurations, 71 boost reasoning >5% — the highest hit rate in the corpus. The (16,19) block is one of the consistent boosters at L16-19.

Across the 21 model variants (10 architecture families) surveyed in john-broadway/rys-sovereign-collection-v2:

Pearson r(baseline reasoning, peak RYS lift) = −0.726. Weak baselines lift more, in their weakest dimension.
Three RYS-recoverable suppression mechanisms identified: under-training scale, MoE routing inefficiency, specialization training trade-off.
One published negative result (SmolLM2-1.7B). RYS is not universal.

v2 attribution: John Broadway, with cross-architecture analysis by Claude (Opus 4.7). Original RYS method by David Ng; circuit-finder toolkit by alainnothere.