DeepSeek-R1-Distill-Qwen-14B

Parameters

14.8B

Published

Jan 22, 2025

DeepSeek-R1-Distill-Qwen-14B is an AI model developed by DeepSeek (China), first published in January 2025. It works in the language domain, on tasks such as language modeling/generation, quantitative reasoning, question answering and 2 more.

Epoch AI has no training-compute estimate for this model. The model has 14,800,000,000 parameters. It was trained on roughly 24B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Qwen2.5-14B. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: DeepSeek
Country of organization: China
Domain: Language
Task: Language modeling/generation, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation
Compute estimation method: Operation counting
Parameters: 14,800,000,000
Dataset size: 24B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: Qwen2.5-14B
Epoch confidence: Speculative

Benchmark results

01	MATH Level 5	mean_score	0.87
02	GPQA Diamond	mean_score	0.45