← All models

DeepSeek: R1 Distill Qwen 32B

deepseek/deepseek-r1-distill-qwen-32b

JSONReasoningStreaming

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new...

Pricing

Input

$0.29 / 1M

Output

$0.29 / 1M

Specs

Context

128,000 tokens

Input

text

Output

text

Knowledge cutoff: 2024-07-31

Released: 2025-01

Supported parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_logprobstop_p

Open weights · HuggingFace

601,125 downloads/mo
1,564 likes
mit text-generation
View on HuggingFace →