Instructions to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF",
	filename="Qwen2.5-Coder-1.5B-RYS-4-9-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/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF with Ollama:
```
ollama run hf.co/john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
```

Unsloth Studio new

How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF to start chatting

Pi new

How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-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-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/Qwen2.5-Coder-1.5B-RYS-4-9-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-1.5B-RYS-4-9-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-Coder-1.5B-RYS-4-9

Qwen2.5-Coder-1.5B-Instruct with layers 4-8 duplicated. Early-stack reasoning circuitry — suppressed by code-specialization training — runs twice on every forward pass.

28 base layers → 33 after duplication. No training, no merging, no weight changes.

Reasoning 23.53% → 52.94% (+29.41). EQ 70.90 → 77.66 (+6.76). Math 0.506 → 0.4687 (−3.73). Peak reasoning Δ across the full 54-config sweep is +35.29% at (6,11) block-5; (4,9) is the best-combined pick.

Results

Metric	Baseline	RYS (4,9)	Delta
Math	0.506	0.4687	−3.73
EQ	70.90	77.66	+6.76
Reasoning	23.53%	52.94%	+29.41

The code-specialist reasoning unlock. Qwen2.5-Coder-1.5B was trained heavily on code, leaving general reasoning under-developed (baseline 23.53%, vs the non-coder Qwen2.5-1.5B-Instruct's 76.47% at the same parameter count). RYS unlocks the dormant general-reasoning circuit. Specialization training trade-off mechanism: where the non-coder sibling has the circuit reliable and RYS adds only +11.76%, the code-specialist's circuit is suppressed enough that the same duplication operation unlocks +29.41% lift (+35.29% at peak).

50 of 54 swept configs boost reasoning >5%. Pick this when you want a tiny coder that can also reason. The published v1 sibling Qwen2.5-1.5B-RYS-4-7-GGUF is the general "balanced daily driver"; this is the code-specialized counterpart.

Usage

llama-server -m Qwen2.5-Coder-1.5B-RYS-4-9-Q4_K_M.gguf -ngl 99

Full sweep data

54 configurations tested. (4,9) block-5 is the best-combined pick. Full per-config sweep + cross-architecture analysis: v2 dataset.

Part of the RYS Sovereign Collection v2.

Where this sits in the Sovereign Collection

v1 — Qwen2.5 cross-scale + Qwen3-32B headline crossover. 5 model repos: 0.5B EQ specialist / 1.5B daily driver / 7B math specialist (+ AWQ) / Qwen3-32B "Big Boy." This Coder variant is the code-specialized sibling of the v1 1.5B daily driver.

v2 — cross-architecture corpus. 21 model variants across 10 architecture families. Inverse correlation (r = −0.726): weak baselines lift more, in their weakest dimension. Three mechanisms: under-training scale (Llama-3.2-1B), MoE routing inefficiency (Granite-3.1-1B-A400M), specialization training trade-off (this model). Plus EQ-amplifier extreme (TinyLlama-1.1B) and a first published negative result (SmolLM2-1.7B). 13 deployable RYS-applied weight repos covering every non-zero-lift variant.

Credit

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