HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/deepseek-ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

family qwen · 12 variants · unknown

provider
deepseek-ai
released
—
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
best scores
AIME 2024: 55.5MATH-500: 92.8GPQA Diamond: 49.1LiveCodeBench: 37.6MATH: 93.6AIME 2025: 40.0Math Olympiad: 56.8

Best scores per benchmark

benchmarkcategorybest score
MATHmath93.6
MATH-500math92.8
Math Olympiadmath56.8
AIME 2024math55.5
GPQA Diamondreasoning49.1
AIME 2025math40.0
LiveCodeBenchcoding37.6

Variants (12)

variantkindquantbitsvRAMdlorgyear
DeepSeek-R1-Distill-Qwen-7Boriginalbf1616.0280,986deepseek-ai2025
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf2.071,162bartowski2025
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf3.018,348lmstudio-community2025
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf16.013,719unsloth2025
DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bitbnb-4bit4bit4,356unsloth2025
DeepSeek-R1-Distill-Qwen-7B-bnb-4bitbnb-4bit4bit3,470unsloth2025
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf4.01,422mradermacher2025
DeepSeek-R1-Distill-Qwen-7Boriginalbf1616.01,200unsloth2025
DeepSeek-R1-Distill-Qwen-7B-GGUFggufgguf16.0255Mungert2025
DLER-R1-7B-Researchoriginalbf1616.085nvidia2025
Polaris-7B-Preview-GGUFggufgguf16.059Mungert2025
OREAL-DeepSeek-R1-Distill-Qwen-7Boriginalbf1616.052internlm2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.