Math and reasoningText

s1

A reasoning model trained on just a thousand problems. It can be told to think longer to answer a hard question more accurately.

Developer
Stanford University, USA
First release
Jan 2025
Latest release
Mar 2025
Sizes
1.5B – 32B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Science and research, Education, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Calculations and formula checks
  • Working through complex problems step by step
  • Training

Where it is used

EducationResearch groupsFinance and analytics

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. s1.1 от 1.5B до 14B
  2. s1.1-32B
  3. s1-32B

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can s1 be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does s1 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 s1 support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download s1 and what does it cost?

The s1 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 reasoningSky-T1NovaSky (Sky Computing Lab, Berkeley) · USACommercial use allowed

A Berkeley reasoning model trained for under 450 dollars. It showed that o1-preview-level reasoning can be reproduced with modest resources.

DetailsMath and reasoningOpenThinkerOpen Thoughts (Stanford, Berkeley and other universities) · USACommercial use allowed

Fully open reasoning models: both weights and training data are published. Newer OpenThinkerAgent versions can carry out multi-step tasks.

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/api/models?author=simplescaling&sort=createdAt&directio. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.