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

TEXT GENERATIONConcurrent 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 a math-focused language model created by espressovi, distilled from Qwen3-8B-Base. This model is specifically optimized for mathematical reasoning tasks, demonstrating strong performance on benchmarks like AIME25. It is designed for applications requiring advanced mathematical problem-solving capabilities.

Loading preview...

Overview

The espressovi/BODHI-qwen-3-8b-distil model is a specialized language model developed by espressovi, focusing on advanced mathematical reasoning. It is a distilled version of the Qwen/Qwen3-8B-Base architecture, specifically enhanced for math-related tasks through a process called Long-CoT distillation.

Key Capabilities

  • Mathematical Reasoning: The model is explicitly designed and optimized for solving complex mathematical problems.
  • Distilled Performance: Leverages distillation from a larger Qwen3-8B-Base model to achieve focused mathematical proficiency.

Performance

  • Achieves 18.82% on the AIME25 benchmark at T=1.0, 16K tokens, and pass@8, indicating its strong capability in competitive mathematics problems.

Good For

  • Applications requiring high accuracy in mathematical problem-solving.
  • Educational tools for advanced math.
  • Research in AI for mathematical reasoning.