xiaozhibro/DeepSeek-R1-Distill-Qwen-7B

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 22, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

The DeepSeek-R1-Distill-Qwen-7B is a 7.6 billion parameter language model developed by DeepSeek AI, distilled from the larger DeepSeek-R1 model and based on the Qwen2.5 architecture. It is specifically fine-tuned to excel in reasoning tasks across math, code, and general problem-solving, leveraging reasoning patterns learned from its larger counterpart. This model offers strong performance in complex reasoning benchmarks, making it suitable for applications requiring robust analytical capabilities.

Loading preview...

DeepSeek-R1-Distill-Qwen-7B: Reasoning Capabilities in a Compact Model

This model is a 7.6 billion parameter variant from the DeepSeek-R1-Distill series, developed by DeepSeek AI. It is based on the Qwen2.5-Math-7B architecture and has been fine-tuned using reasoning data generated by the much larger DeepSeek-R1 model. The core innovation lies in demonstrating that complex reasoning patterns from large models can be effectively distilled into smaller, more efficient models.

Key Capabilities & Features

  • Reasoning Distillation: Leverages reasoning patterns from the 671B parameter DeepSeek-R1, which was trained via large-scale reinforcement learning (RL) to develop advanced chain-of-thought (CoT) capabilities.
  • Enhanced Performance: Achieves strong results on various benchmarks, including AIME 2024 (55.5 pass@1), MATH-500 (92.8 pass@1), and LiveCodeBench (37.6 pass@1), demonstrating its proficiency in mathematical, coding, and general reasoning tasks.
  • Optimized for Reasoning: Designed to engage in thorough reasoning, with recommendations to enforce a "\n" prefix to ensure detailed thought processes.
  • Commercial Use: Licensed under the MIT License, supporting commercial use and modifications.

Good For

  • Complex Problem Solving: Excels in tasks requiring step-by-step reasoning, such as mathematical proofs, code generation, and logical puzzles.
  • Resource-Constrained Environments: Provides high reasoning capabilities in a 7.6B parameter model, making it more accessible than its larger counterparts.
  • Research and Development: Ideal for researchers exploring model distillation techniques and the transfer of reasoning abilities from large to small LLMs.