Math and reasoning · NVIDIA

OpenMath Nemotron 7B

Hugging Face: nvidia/OpenMath-Nemotron-7B · checked 2026-10-13

Maths specialist trained on OpenMathReasoning; supports tool-integrated reasoning.

Datasheet

Maker	NVIDIA
Parameters	7.62 BVerifiedsafetensors.total from the HF API Source
Licence	CC-BY-4.0Verified
Access	Public download
Task (HF pipeline)	text-generation
First published on HF	2025-04-22
Last updated on HF	2025-04-30
Weights in memory	15 GB at 16-bit · 4.6 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build.

Benchmark

74.8%

AIME 2024, pass@1 · #5 of 7 scored in this category

AIME24, chain-of-thought pass@1 (the card also gives maj@64 in brackets). Source

See the full math and reasoning ranking

The description summarises the model card at https://huggingface.co/nvidia/OpenMath-Nemotron-7B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.