DeepSeek-R1 or QwQ: which reasoning model to pick
Both reason step by step before answering, both are in Ollama, and both licenses are permissive: MIT for R1 and Apache 2.0 for QwQ. R1 offers sizes from 1.5B to 671B, distilled versions included, and runs on a CPU, so you can start small and scale as load grows. QwQ exists in a single 32B size and needs a GPU, but it is a ready reasoning model for calculations, formula checks and working through problems. The catalog marks QwQ as not supporting Russian and makes no claim for R1, so for Russian text you should test both on your own data.
Comparison based on catalog data
| Parameter | DeepSeek-R1 | QwQ |
|---|---|---|
| Category | Text | Math and reasoning, Text |
| Developer | DeepSeek, China | Qwen (Alibaba), China |
| Releases | Jan 2025 – May 2025 | Nov 2024 – Mar 2025 |
| Sizes | 1,5B – 671B | 32B |
| Hardware | Laptop, 1 GPU, Cluster | 1 GPU |
| Commercial use | Commercial use allowed | Commercial use allowed |
| License | MIT | Apache 2.0 |
| Russian | Not stated | Not supported |
| Ollama | Yes | Yes |
| Without GPU | Yes | No |
| Tasks |
|
|
Choose DeepSeek-R1 if
- You want a size range: from 1.5B on a CPU up to 671B on a cluster
- The MIT license matters to you
- Legal and finance work: contracts and disputed cases broken down step by step
Choose QwQ if
- A single 32B size on a GPU is fine for you
- You specifically need Apache 2.0
- Maths, engineering and training tasks with step-by-step breakdowns
Other comparisons
- Qwen or GigaChat: which to choose for business
- Qwen or Llama: which to choose for business
- GigaChat or YandexGPT: which to choose for business
- DeepSeek or Qwen: which to choose for business
- Gemma or Llama: which to choose for business
- Mistral or Llama: which to choose for business
- gpt-oss or Qwen: which one to run on your own server
- Llama or DeepSeek: which to run inside your own perimeter
- Mistral or Qwen: which to choose for business
- Gemma or Phi: small models for modest hardware
- YandexGPT or Qwen: which to choose for Russian
- T-Pro or GigaChat: which one for a Russian company
Need a model for your task?
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
- SelectThe model and size for your task and hardware budget
- DeployOn your server or in a closed network, with an API
- Fine-tuneOn your data, or connect a knowledge base
- IntegrateInto your CRM, ERP, bot, website or team chat