HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/deepseek-ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

family qwen · 14 variants · unknown

provider
deepseek-ai
released
—
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
best scores
AIME 2024: 33.75MATH-500: 88.34GPQA Diamond: 33.8LiveCodeBench: 16.9MATH: 84.31AIME 2025: 27.29GPQA: 37.91IFEval: 44.05Codeforces: 28.5HumanEval: 73.0

Best scores per benchmark

benchmarkcategorybest score
MATH-500math88.34
MATHmath84.31
HumanEvalcoding73.0
IFEvalinstruction-following44.05
GPQAreasoning37.91
GPQA Diamondreasoning33.8
AIME 2024math33.75
Codeforcescoding28.5
AIME 2025math27.29
LiveCodeBenchcoding16.9

Variants (14)

variantkindquantbitsvRAMdlorgyear
DeepSeek-R1-Distill-Qwen-1.5Boriginalbf1616.0607,200deepseek-ai2025
DeepSeek-R1-Distill-Qwen-1.5B-GGUFggufgguf16.056,723unsloth2025
DeepSeek-R1-Distill-Qwen-1.5B-GGUFggufgguf2.020,902bartowski2025
DeepSeek-R1-Distill-Qwen-1.5B-GGUFggufgguf3.06,734lmstudio-community2025
DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bitbnb-4bit4bit6,718unsloth2025
Nemotron-Research-Reasoning-Qwen-1.5Boriginalbf1616.02,786nvidia2025
DeepSeek-R1-Distill-Qwen-1.5B-bnb-4bitbnb-4bit4bit2,506unsloth2025
DeepSeek-R1-Distill-Qwen-1.5Boriginalbf1616.01,539unsloth2025
DLER-R1-1.5B-Researchoriginalbf1616.0550nvidia2025
Nemotron-Research-Reasoning-Qwen-1.5B-GGUFggufgguf16.0454Mungert2025
DeepSeek-R1-Distill-Qwen-1.5B-Q4_0-GGUFggufgguf4.0277ggml-org2025
DeepSeek-R1-Distill-Qwen-1.5B-GGUFggufgguf16.0195Mungert2025
DeepCoder-1.5B-Preview-GGUFggufgguf16.0160Mungert2025
ZR1-1.5B-GGUFggufgguf16.0132Mungert2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.