LimitlessMindd/DeepSeek-R1-Distill-Llama-70B

TEXT GENERATIONPricing:Input $2.88 / Output $2.88Concurrent Unit Cost:4Model Size:70BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 21, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

DeepSeek-R1-Distill-Llama-70B is a 70 billion parameter language model developed by DeepSeek-AI, distilled from the larger DeepSeek-R1 model and based on Llama-3.3-70B-Instruct. It is specifically fine-tuned using reasoning data generated by DeepSeek-R1, which itself was developed through large-scale reinforcement learning. This model excels in complex reasoning tasks across math, code, and general English benchmarks, offering a powerful solution for applications requiring advanced problem-solving capabilities with a 32768 token context length.

Loading preview...

DeepSeek-R1-Distill-Llama-70B: Reasoning Capabilities in a Distilled Model

DeepSeek-R1-Distill-Llama-70B is a 70 billion parameter model from DeepSeek-AI, part of a series of distilled models designed to transfer the advanced reasoning capabilities of the larger DeepSeek-R1 into more accessible architectures. DeepSeek-R1 itself is a first-generation reasoning model developed through a novel reinforcement learning (RL) approach, which demonstrated that reasoning can be incentivized purely through RL without initial supervised fine-tuning (SFT).

Key Capabilities and Features

  • Reasoning Distillation: This model is fine-tuned using high-quality reasoning data generated by the powerful DeepSeek-R1, allowing smaller models to inherit complex problem-solving patterns.
  • Strong Performance: It achieves competitive results across various benchmarks, including AIME 2024 (70.0 pass@1), MATH-500 (94.5 pass@1), GPQA Diamond (65.2 pass@1), and LiveCodeBench (57.5 pass@1), often outperforming models like GPT-4o and Claude-3.5-Sonnet in specific reasoning categories.
  • Llama-3.3 Base: Built upon the Llama-3.3-70B-Instruct base, it leverages a well-established and performant architecture.
  • Extended Context Length: Supports a context window of 32,768 tokens, suitable for handling lengthy and complex problem descriptions.

When to Use This Model

This model is particularly well-suited for:

  • Complex Reasoning Tasks: Ideal for applications requiring advanced logical deduction, mathematical problem-solving, and code generation.
  • Benchmarking and Research: Provides a strong baseline for research into distilled reasoning capabilities and RL-driven model development.
  • High-Performance Applications: Offers robust performance in scenarios where accuracy in reasoning is critical, comparable to larger proprietary models.

Finetunes
1 models