espressovi/BODHI-qwen-3-8b-distil

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 20, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

BODHI-qwen-3-8b-distil is an 8 billion parameter Qwen3-based language model developed by espressovi, specifically distilled for mathematical reasoning. It features a 32768-token context length and excels in complex math tasks, achieving 18.82% on AIME25. This model is optimized for scenarios requiring strong mathematical problem-solving capabilities.

Loading preview...

Overview

The espressovi/BODHI-qwen-3-8b-distil is an 8 billion parameter language model derived from Qwen/Qwen3-8B-Base. It has been specifically developed through a Long-CoT distillation process, making it highly specialized for mathematical reasoning tasks. With a substantial context length of 32768 tokens, it is designed to handle complex mathematical problems requiring extensive context.

Key Capabilities

  • Advanced Mathematical Reasoning: Optimized for solving intricate math problems through its unique distillation process.
  • Strong Performance on AIME25: Achieves a notable 18.82% on the AIME25 benchmark, indicating its proficiency in competitive mathematics.
  • Extended Context Window: Supports a 32768-token context, allowing for the processing of longer problem descriptions and solution steps.

Good For

  • Mathematical Problem Solving: Ideal for applications requiring accurate and robust solutions to mathematical challenges.
  • Educational Tools: Can be integrated into platforms for teaching or assisting with advanced mathematics.
  • Research in AI for Math: Useful for researchers exploring methods for improving AI's mathematical capabilities, particularly through distillation techniques.