Aesdi90/DeepSeek-32B-Bare-Mind
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Apr 3, 2026License:mitArchitecture:Transformer0.0K Open Weights Cold

Aesdi90/DeepSeek-32B-Bare-Mind is a 32.8 billion parameter distilled reasoning model developed by DeepSeek AI, based on the Qwen2.5-32B architecture. It is part of the DeepSeek-R1-Distill series, which leverages reasoning patterns from larger DeepSeek-R1 models. This model is specifically fine-tuned to excel in complex reasoning tasks across mathematics, code, and general problem-solving, demonstrating strong performance on benchmarks like AIME 2024 and MATH-500.

Loading preview...