DeepSeek-R1-Distill-Qwen-32B-GGUF

Home/Models/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF

unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF

kind: gguf
quant: gguf (16-bit)
family: qwen
modality: —
root model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
provider: unsloth
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 23,089
likes: 158
created: —
last modified: 2025-01-25T09:06:07+00:00 (2025)
huggingface: https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
tags: transformersggufdeepseekqwenqwen2unslothenarxiv:2501.12948base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bbase_model:quantized:deepseek-ai/DeepSeek-R1-Distill-Qwen-32Blicense:apache-2.0endpoints_compatibleregion:usconversational

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.