Instructions to use bytecodehr/qwen3-8b-rails with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bytecodehr/qwen3-8b-rails with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bytecodehr/qwen3-8b-rails")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bytecodehr/qwen3-8b-rails", dtype="auto")

llama-cpp-python

How to use bytecodehr/qwen3-8b-rails with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bytecodehr/qwen3-8b-rails",
	filename="qwen3-8b-rails-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bytecodehr/qwen3-8b-rails 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 bytecodehr/qwen3-8b-rails:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bytecodehr/qwen3-8b-rails:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bytecodehr/qwen3-8b-rails:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bytecodehr/qwen3-8b-rails: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 bytecodehr/qwen3-8b-rails:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bytecodehr/qwen3-8b-rails: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 bytecodehr/qwen3-8b-rails:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bytecodehr/qwen3-8b-rails:Q4_K_M

Use Docker

docker model run hf.co/bytecodehr/qwen3-8b-rails:Q4_K_M

LM Studio
Jan

vLLM

How to use bytecodehr/qwen3-8b-rails with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bytecodehr/qwen3-8b-rails"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bytecodehr/qwen3-8b-rails",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bytecodehr/qwen3-8b-rails:Q4_K_M

SGLang

How to use bytecodehr/qwen3-8b-rails with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bytecodehr/qwen3-8b-rails" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bytecodehr/qwen3-8b-rails",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bytecodehr/qwen3-8b-rails" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bytecodehr/qwen3-8b-rails",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bytecodehr/qwen3-8b-rails with Ollama:
```
ollama run hf.co/bytecodehr/qwen3-8b-rails:Q4_K_M
```

Unsloth Studio

How to use bytecodehr/qwen3-8b-rails 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 bytecodehr/qwen3-8b-rails 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 bytecodehr/qwen3-8b-rails to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bytecodehr/qwen3-8b-rails to start chatting

How to use bytecodehr/qwen3-8b-rails with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bytecodehr/qwen3-8b-rails: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": "bytecodehr/qwen3-8b-rails:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bytecodehr/qwen3-8b-rails with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bytecodehr/qwen3-8b-rails: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 bytecodehr/qwen3-8b-rails:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use bytecodehr/qwen3-8b-rails with Docker Model Runner:
```
docker model run hf.co/bytecodehr/qwen3-8b-rails:Q4_K_M
```

Lemonade

How to use bytecodehr/qwen3-8b-rails with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bytecodehr/qwen3-8b-rails:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-8b-rails-Q4_K_M

List all available models

lemonade list

qwen3-8b-rails

An 8B parameter dense model fine-tuned for Ruby on Rails code generation. Trained on 111,000 samples extracted from our own internal Rails projects. Small enough to run on a laptop.

Built by Bytecode.

Model Details

Property	Value
Base model	Qwen3-8B
Architecture	Qwen3 dense (8B parameters)
Training method	QLoRA (rank 16) via Unsloth
Training data	111K samples from internal Rails projects
Training cost	~$21 (A100 80GB, ~17 hours)
Quantization	GGUF Q4_K_M (5.03 GB)

What it does

This model writes idiomatic Ruby on Rails code following specific conventions:

Devise authentication
Namespaced concerns instead of service objects
Sidekiq instead of Solid Queue
State-as-records instead of boolean flags
DaisyUI drawer layouts instead of ActiveAdmin

The 8B model is the lightweight option — fast enough for inline code completion, small enough to run alongside your development server without swapping.

Usage with Ollama

# Download and run
ollama run bytecodehr/qwen3-8b-rails

# Example prompt
ollama run bytecodehr/qwen3-8b-rails "Write a Rails migration for a subscriptions table with plan, status, and billing cycle"

Memory requirements

Format	GGUF Size	Min RAM	Recommended
Q4_K_M	5.03 GB	8 GB	16 GB

Fits comfortably on any modern laptop. GGUF file size + 2–3 GB for KV cache.

Training

Trained with LoRA (rank 16, alpha 16) on attention projection layers. Only 0.78% of parameters were trained. The full training run took ~17 hours on a single A100 80GB GPU.

The dataset:

Our internal Rails projects
15-step cleaning and deduplication pipeline
111K final training samples with contrastive pairs
Source diversity cap at 20% per repository

Full details in our blog posts:

Why Ruby for LLMs?

Ruby uses 42–45% fewer tokens than TypeScript across every major LLM tokenizer. Fewer tokens means more code in the context window, faster generations, and lower costs. Read our analysis: Why Ruby Is the Better Language for LLM-Powered Development.

Other models

bytecodehr/qwen3-coder-30b-rails — 31B MoE flagship model (18–21 GB)
bytecodehr/qwen2.5-coder-7b-rails — 7B LoRA adapter
bytecodehr/qwen2.5-coder-3b-rails — 3B LoRA adapter

Downloads last month: 6

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for bytecodehr/qwen3-8b-rails

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(1465)

this model