bytecodehr/qwen3-coder-30b-rails

qwen3-coder-30b-rails

A 31B parameter Mixture-of-Experts model fine-tuned for Ruby on Rails code generation. Trained on 111,000 samples extracted from our own internal Rails projects.

Built by Bytecode.

Model Details

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

It generates code that follows these patterns without prompt engineering — the conventions are baked into the weights.

Usage with Ollama

# Download and run
ollama run bytecodehr/qwen3-coder-30b-rails

# Example prompt
ollama run bytecodehr/qwen3-coder-30b-rails "Write a Rails controller for managing user subscriptions with state transitions"

Memory requirements

Rule of thumb: GGUF file size + 2–4 GB for KV cache and overhead.

Training

Trained with LoRA (rank 16, alpha 16) on attention projection layers (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj). Only 0.78% of parameters were trained.

The dataset pipeline:

1. 1.Extracted code from our internal Rails projects
2. 2.15-step cleaning and deduplication pipeline
3. 3.111K final training samples
4. 4.Includes 29 contrastive pairs (wrong way vs right way)
5. 5.Source diversity cap at 20% per repository

Full details in our blog posts:

• —Part 1: Dataset Engineering
• —Part 2: Training, Quantization, and Deployment

Why Ruby for LLMs?

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

Other models

• —bytecodehr/qwen3-8b-rails — 8B dense model, runs on laptops (5 GB)
• —bytecodehr/qwen2.5-coder-7b-rails — 7B LoRA adapter
• —bytecodehr/qwen2.5-coder-3b-rails — 3B LoRA adapter