Solar
Models from Korea's Upstage. Solar Open 2 is built for office document work: 250 billion parameters, 15 billion active; languages are English, Korean and Japanese.
- Developer
- Upstage, South Korea
- First release
- Dec 2023
- Latest release
- Jul 2026
- Sizes
- 10.7B – 250B-A15B
- License
- Commercial use with conditionsSOLAR-10.7B: Apache 2.0; Solar Open and Open 2: Upstage Solar License (based on Apache 2.0: commercial use allowed, but a fine-tuned model's name must start with Solar, plus a Built with Solar notice)
- Russian
- Not supported
- Ready-made builds
- GGUF, AWQ
- Running
- Available in OllamaNeeds a GPU
- Industries
- Documents and accounting, Software development
What it does
- Working with office documents
- Agents for routine tasks
- Help for developers
Where it is used
Hardware requirements
Versions
- Solar Open 2 250B
- Solar Open 100B
- Solar Pro Preview
- SOLAR-10.7B
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 Solar be used in a commercial project?
With conditions. License: SOLAR-10.7B: Apache 2.0; Solar Open and Open 2: Upstage Solar License (based on Apache 2.0: commercial use allowed, but a fine-tuned model's name must start with Solar, plus a Built with Solar notice). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does Solar need?
At minimum: One GPU with 16–80 GB — mid-size 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 Solar support Russian?
No. The model card lists its languages and Russian is not among them.
Where can I download Solar and what does it cost?
The Solar 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
Korean-English models from LG. Most of the line is non-commercial, but the flagship K-EXAONE 2.0 with 750 billion parameters is released under Apache 2.0.
DetailsTextKananaKakao · South KoreaCommercial use with conditionsCompact Korean-English models from Kakao. Kanana 2 30B-A3B is fast thanks to MoE; small 1–3B versions suit a regular PC.
DetailsTextMistralMistral AI · FranceCommercial use with conditionsEuropean models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).
DetailsSource: huggingface.co/upstage/Solar-Open2-250B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


