HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/Qwen/Qwen/Qwen2.5-1.5B-Instruct

Qwen/Qwen2.5-1.5B-Instruct

family qwen · 13 variants · unknown

provider
Qwen
released
—
huggingface
https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct
best scores
GPQA: 31.6MMLU-Pro: 47.5Humanity's Last Exam: 11.8LiveCodeBench: 28.6SciCode: 2.2AIME 2024: 55.5AIME 2025: 45.6

Best scores per benchmark

benchmarkcategorybest score
AIME 2024math55.5
MMLU-Proknowledge47.5
AIME 2025math45.6
GPQAreasoning31.6
LiveCodeBenchcoding28.6
Humanity's Last Examknowledge11.8
SciCodecoding2.2

Variants (13)

variantkindquantbitsvRAMdlorgyear
Qwen2.5-1.5B-Instruct-AWQawqawq839,752Qwen2024
Qwen2.5-1.5B-Instruct-GGUFggufgguf214,615Qwen2024
Qwen2.5-1.5B-Instruct-unsloth-bnb-4bitbnb-4bit4bit70,188unsloth2025
Qwen2.5-1.5B-Instructoriginalbf1616.046,122unsloth2025
Qwen2.5-1.5B-Instruct-bnb-4bitbnb-4bit4bit35,264unsloth2025
Qwen2.5-1.5B-Instruct-GGUFggufgguf2.026,061bartowski2024
Qwen2.5-1.5B-Instruct-GPTQ-Int4gptqgptq7,228Qwen2024
Qwen2.5-1.5B-Instruct-GGUFggufgguf3.04,141lmstudio-community2024
Qwen2.5-1.5B-Instruct-GPTQ-Int8gptqgptq1,010Qwen2024
Qwen2.5-1.5B-Instruct-MLX-4bitmlxmlx570lmstudio-community2024
Qwen2.5-1.5B-Instruct-MLX-8bitmlxmlx402lmstudio-community2024
Arch-Router-1.5B-GGUFggufgguf16.0187Mungert2025
OpenReasoning-Nemotron-1.5B-GGUFggufgguf16.0116Mungert2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.