ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Apr 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth is a 4 billion parameter Qwen3 model, fine-tuned by ermiaazarkhalili using Unsloth for optimized reasoning distillation. It leverages a 2,048 token context length and was trained on the Claude Reasoning Distillation dataset to enhance chain-of-thought capabilities. This model is specifically designed to improve reasoning performance, making it suitable for tasks requiring structured thought processes.

Loading preview...

Model Overview

This model, developed by ermiaazarkhalili, is a fine-tuned version of the 4-billion parameter Qwen3-4B base model, optimized for reasoning distillation. It utilizes Unsloth for efficient training, achieving 2x faster training times and 60% less VRAM consumption compared to standard methods. The model was specifically trained on the claude-reasoning-distillation dataset, which comprises 10,477 samples featuring Claude's reasoning traces with <think> blocks to facilitate chain-of-thought learning.

Key Capabilities

  • Enhanced Reasoning: Specialized in distilling reasoning processes, particularly chain-of-thought, from Claude Opus.
  • Efficient Training: Benefits from Unsloth's optimizations for faster and more memory-efficient fine-tuning.
  • Compact Size: A 4B parameter model, offering a balance between performance and resource requirements.
  • Context Window: Supports a 2,048 token context length, suitable for moderate-length reasoning tasks.
  • GGUF Availability: Quantized GGUF versions are provided for CPU and edge inference, enhancing deployment flexibility.

Good For

  • Complex Problem Solving: Ideal for applications requiring step-by-step logical deduction and structured reasoning.
  • Educational Tools: Can be used to generate explanations or demonstrate problem-solving methodologies.
  • Research in Reasoning: A valuable base for further research into improving LLM reasoning capabilities.
  • Resource-Constrained Environments: Its efficient training and GGUF availability make it suitable for deployment on less powerful hardware.

Finetunes
2 models