DeepSeek-R1-Distill-Qwen-32B

Home/Models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
provider: deepseek-ai
license: mit
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 832,252
likes: 1,583
created: —
last modified: 2025-02-24T03:31:29+00:00 (2025)
huggingface: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
tags: transformerssafetensorsqwen2text-generationconversationalarxiv:2501.12948license:mittext-generation-inferenceendpoints_compatibleregion:usdeploy:sagemaker

benchmark	category	score	context	conf	evidence
MATH-500	math	94.3		high	`\| DeepSeek-R1-Distill-Qwen-32B \| 72.6 \| 83.3 \| 94.3 \| 62.1 \| 57.2 \| 1691 \|`
AIME 2024	math	72.6		high	`\| DeepSeek-R1-Distill-Qwen-32B \| 72.6 \| 83.3 \| 94.3 \| 62.1 \| 57.2 \| 1691 \|`
GPQA Diamond	reasoning	62.1		high	`\| DeepSeek-R1-Distill-Qwen-32B \| 72.6 \| 83.3 \| 94.3 \| 62.1 \| 57.2 \| 1691 \|`
LiveCodeBench	coding	57.2		high	`\| DeepSeek-R1-Distill-Qwen-32B \| 72.6 \| 83.3 \| 94.3 \| 62.1 \| 57.2 \| 1691 \|`
MATH	math	16.0	Math	medium	`\| Math \| AIME 2024 (Pass@1) \| 16.0 \| 9.3 \| 39.2 \| 63.6 \| 79.2 \| 79.8 \|`

none scraped.