Math and reasoningText

AceMath / AceReason

NVIDIA models for maths and reasoning based on Qwen. AceReason was fine-tuned with reinforcement learning first on maths, then on code.

Developer
NVIDIA, USA
First release
Jan 2025
Latest release
Jun 2025
Sizes
1.5B – 72B
License
Commercial use with conditionsAceMath: CC-BY-NC 4.0 (non-commercial); AceReason and AceMath-RL: NVIDIA Open Model License
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Science and research, Finance, Software development, Education
Deploy on your server Hugging Face

What it does

  • Calculations and formula checks
  • Complex analytics with step-by-step breakdowns
  • Working through programming problems
  • Training

Where it is used

Finance and analyticsEngineering companiesIT departmentsEducation

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. AceReason-Nemotron-1.1-7B
  2. AceReason-Nemotron 7B и 14B
  3. AceMath-RL-Nemotron-7B
  4. AceMath 1.5B – 72B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can AceMath / AceReason be used in a commercial project?

With conditions. License: AceMath: CC-BY-NC 4.0 (non-commercial); AceReason and AceMath-RL: NVIDIA Open Model License. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does AceMath / AceReason need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does AceMath / AceReason support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download AceMath / AceReason and what does it cost?

The AceMath / AceReason weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Math and reasoningQwen2.5-MathQwen (Alibaba) · ChinaCommercial use with conditions

Maths versions of Qwen: they solve problems step by step and can calculate via code. Includes reward models that check each step of a solution.

DetailsTextNVIDIA NemotronNVIDIA · USACommercial use with conditions

NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only).

DetailsMath and reasoningLight-R1Qihoo 360 · ChinaCommercial use allowed

Reasoning models from Qihoo 360: a standard Qwen2.5 was fine-tuned for long reasoning using an open recipe; data and code are published.

Details

Source: huggingface.co/nvidia/AceReason-Nemotron-1.1-7B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.