DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Llama-70B

About DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Llama-70B is a distilled model based on Llama-3.3-70B-Instruct. As part of the DeepSeek-R1 series, it was fine-tuned using samples generated by DeepSeek-R1 and demonstrates excellent performance across mathematics, programming, and reasoning tasks. The model achieved impressive results in various benchmarks including AIME 2024, MATH-500, and GPQA Diamond, showcasing its strong reasoning capabilities

Metadata

Create on

License

MIT

Provider

DeepSeek

Specification

State

Deprecated

Architecture

Calibrated

No

Mixture of Experts

No

Total Parameters

70B

Activated Parameters

Reasoning

No

Precision

FP8

Context length

33K

Max Tokens

Ready to accelerate your AI development?

Ready to accelerate your AI development?

Ready to accelerate your AI development?

© 2026 SiliconFlow

© 2026 SiliconFlow

© 2026 SiliconFlow