Math and reasoningCode

DeepScaleR, DeepCoder, DeepSWE

Small models fine-tuned with reinforcement learning: DeepScaleR (1.5B) solves olympiad maths, DeepCoder writes code, DeepSWE works as a developer agent. Recipes and data are open.

Developer: Agentica (Berkeley, Sky Computing Lab) and Together AI, USA
First release: Feb 2025
Latest release: Jul 2025
Sizes: 1.5B – 32B
License: Commercial use allowedMIT
Russian: Not supported
Ready-made builds: GGUF
Running: Available in OllamaAlso runs without a GPU
Industries: Education, Software development, Science and research

Deploy on your server Hugging Face GitHub

What it does

Solving maths problems with step-by-step working
Generating and checking code
An agent for fixing bugs in a repository

Where it is used

EducationDevelopmentResearch

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

Jul 2025DeepSWE-Preview 32B
Apr 2025DeepCoder-14B и 1.5B
Feb 2025DeepScaleR-1.5B-Preview

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library

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 DeepScaleR, DeepCoder, DeepSWE be used in a commercial project?

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

What hardware does DeepScaleR, DeepCoder, DeepSWE 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 DeepScaleR, DeepCoder, DeepSWE support Russian?

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

Where can I download DeepScaleR, DeepCoder, DeepSWE and what does it cost?

The DeepScaleR, DeepCoder, DeepSWE 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

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

A reasoning model that thinks step by step before answering. Strong at calculations, logic and code; compact distilled versions are available.

Details Math 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.

Details 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.

Details

Source: huggingface.co/agentica-org/DeepSWE-Preview. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.