Sky-T1
A Berkeley reasoning model trained for under 450 dollars. It showed that o1-preview-level reasoning can be reproduced with modest resources.
- Developer
- NovaSky (Sky Computing Lab, Berkeley), USA
- First release
- Jan 2025
- Latest release
- Feb 2025
- Sizes
- 7B – 32B
- License
- Commercial use allowedApache 2.0 (32B versions; the 7B has no license stated on the card)
- Russian
- Not supported
- Ready-made builds
- GGUF
- Running
- On your own serverNeeds a GPU
- Industries
- Science and research, Education
What it does
- Calculations and formula checks
- Working through problems step by step
- A base for your own reasoning fine-tuning
Where it is used
Hardware requirements
Versions
- Sky-T1-7B и Sky-T1-mini
- Sky-T1-32B-Flash
- Sky-T1-32B-Preview
How to run it
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 Sky-T1 be used in a commercial project?
Yes. License: Apache 2.0 (32B versions; the 7B has no license stated on the card). It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Sky-T1 need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does Sky-T1 support Russian?
No. The model card lists its languages and Russian is not among them.
Where can I download Sky-T1 and what does it cost?
The Sky-T1 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.
Similar models
A reasoning model trained on just a thousand problems. It can be told to think longer to answer a hard question more accurately.
DetailsMath and reasoningOpenThinkerOpen Thoughts (Stanford, Berkeley and other universities) · USACommercial use allowedFully open reasoning models: both weights and training data are published. Newer OpenThinkerAgent versions can carry out multi-step tasks.
DetailsMath and reasoningQwQQwen (Alibaba) · ChinaCommercial use allowedQwen's first open reasoning model: it thinks step by step before answering and comes close to DeepSeek-R1 on maths tasks with only 32B parameters.
DetailsSource: huggingface.co/api/models?author=NovaSky-AI&sort=createdAt&direction=-. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


