HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

ZR1-1.5B-GGUF

Mungert/ZR1-1.5B-GGUF

kind
gguf
quant
gguf (16-bit)
family
misc
modality
text-generation
root model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
provider
Mungert
license
mit
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
132
likes
3
created
—
last modified
2025-09-24T15:40:54+00:00 (2025)
huggingface
https://huggingface.co/Mungert/ZR1-1.5B-GGUF
tags
transformersgguftext-generationendataset:AI-MO/NuminaMath-CoTdataset:codeparrot/appsdataset:deepmind/code_contestsdataset:BAAI/TACOdataset:MatrixStudio/Codeforces-Python-Submissionsarxiv:2502.01456arxiv:2503.07572base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bbase_model:quantized:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Blicense:mitendpoints_compatibleregion:usconversational

Benchmark scores (13)

benchmarkcategoryscorecontextconfevidence
MATH-500math88.34high| ZR1-1.5B | 33.75% | 27.29% | 72.06% | 59.17% | **37.91%** | 88.34% | 33.52% | 56.87% |
MATHmath62.0Qwen2.5-Math-7B-Instructmedium| Qwen2.5-Math-7B-Instruct | 62% | 45.83% | 16.67% | 4% |
MATHmath60.42high| ZR1-1.5B | **74%** | 60.42% | **39.74%** | **12%** |
MATHmath56.0Qwen2.5-Math-72B-Instructmedium| Qwen2.5-Math-72B-Instruct | 56% | 59.38% | 42.31% | 42% |
MATHmath49.0Qwen2.5-Math-1.5B-Instructmedium| Qwen2.5-Math-1.5B-Instruct | 49% | 36.46% | 0% | 0% |
GPQAreasoning37.91high| ZR1-1.5B | 33.75% | 27.29% | 72.06% | 59.17% | **37.91%** | 88.34% | 33.52% | 56.87% |
MATHmath37.01Qwen-2.5-Math-7B-Instructmedium| Qwen-2.5-Math-7B-Instruct | 37.01% | 2048 |
AIME 2024math33.75high| ZR1-1.5B | 33.75% | 27.29% | 72.06% | 59.17% | **37.91%** | 88.34% | 33.52% | 56.87% |
MATHmath32.25Qwen-2.5-Math-1.5B-Instructmedium| Qwen-2.5-Math-1.5B-Instruct | 32.25% | 2048 |
AIME 2025math27.29high| ZR1-1.5B | 33.75% | 27.29% | 72.06% | 59.17% | **37.91%** | 88.34% | 33.52% | 56.87% |
MATHmath26.67Qwen2.5-Math-72B-Instruct (greedy)medium| Qwen2.5-Math-72B-Instruct (greedy) | 26.67% | 6.67% | 59.04% | 46.67% | 43.94% | 85.40% | 42.65% | 50.37% |
MATHmath20.0Qwen2.5-Math-7B-Instruct (greedy)medium| Qwen2.5-Math-7B-Instruct (greedy) | 20% | 3.33% | 46.99% | 31.11% | 32.32% | 83% | 37.13% | 42.22% |
MATHmath10.0Qwen2.5-Math-1.5B-Instruct (greedy)medium| Qwen2.5-Math-1.5B-Instruct (greedy) | 10% | 6.67% | 42.17% | 26.67% | 28.28% | 75.20% | 28.31% | 40.74% |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.