maksimbbbi/DeepSeek-R1-Distill-Llama-8B

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 29, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

DeepSeek-R1-Distill-Llama-8B is an 8 billion parameter language model developed by DeepSeek-AI, distilled from the larger DeepSeek-R1 model and based on Llama-3.1-8B. It is specifically fine-tuned using reasoning data generated by DeepSeek-R1, aiming to transfer advanced reasoning patterns to a smaller, more efficient architecture. This model excels in mathematical, coding, and general reasoning tasks, offering strong performance for applications requiring robust analytical capabilities with a 32K context length.

Loading preview...

DeepSeek-R1-Distill-Llama-8B Overview

DeepSeek-R1-Distill-Llama-8B is an 8 billion parameter model developed by DeepSeek-AI, part of a series of distilled models designed to transfer the advanced reasoning capabilities of the larger DeepSeek-R1 into more compact architectures. DeepSeek-R1 itself is a first-generation reasoning model trained primarily through large-scale reinforcement learning (RL), demonstrating capabilities like self-verification and generating complex chains-of-thought without initial supervised fine-tuning (SFT).

Key Capabilities

  • Reasoning Distillation: This model benefits from reasoning patterns distilled from the powerful DeepSeek-R1, which was trained to excel in complex problem-solving.
  • Strong Performance: Achieves competitive results across various benchmarks, particularly in mathematical reasoning (AIME 2024 pass@1: 50.4, MATH-500 pass@1: 89.1), coding (LiveCodeBench pass@1: 39.6, CodeForces rating: 1205), and general reasoning tasks.
  • Llama-3.1 Base: Built upon the Llama-3.1-8B architecture, providing a familiar and robust foundation.
  • Extended Context: Supports a context length of 32,768 tokens, suitable for handling longer and more complex inputs.

When to Use This Model

  • Resource-Efficient Reasoning: Ideal for applications requiring strong reasoning abilities where the computational cost of larger models is prohibitive.
  • Mathematical and Coding Tasks: Particularly well-suited for tasks involving complex calculations, problem-solving, and code generation.
  • Research and Development: Useful for researchers exploring model distillation techniques and the transfer of reasoning capabilities from larger to smaller models.

DeepSeek-AI emphasizes that these distilled models demonstrate that smaller architectures can achieve powerful performance when effectively trained with high-quality reasoning data.