TimesFM or Chronos: which forecasting model to pick
Both models forecast a time series without training on your data and run on a CPU. Google's TimesFM is newer: version 3.0 shipped in 2026-08, but that is the one under a non-commercial license, while versions 1.0 to 2.5 stay open for business under Apache 2.0. Amazon's Chronos is Apache 2.0 across the whole line, and the latest Chronos-2 from 2025-10 accounts for external factors: prices, promotions, weather. Chronos sizes start at 8M, so it fits a modest server, while TimesFM starts at 200M. The catalog lists both for retail, manufacturing and finance; the choice depends on whether you need external factors and how much the newest version matters.
Comparison based on catalog data
| Parameter | TimesFM | Chronos |
|---|---|---|
| Category | Forecasting | Forecasting |
| Developer | Google, USA | Amazon, USA |
| Releases | May 2024 – Aug 2026 | Mar 2024 – Oct 2025 |
| Sizes | 200M – 500M | 8M – 710M |
| Hardware | Laptop, 1 GPU | Laptop |
| Commercial use | Commercial use with conditions | Commercial use allowed |
| License | Versions 1.0 to 2.5: Apache 2.0; TimesFM 3.0: non-commercial license | Apache 2.0 |
| Russian | Not applicable | Not applicable |
| Ollama | No | No |
| Without GPU | Yes | Yes |
| Tasks |
|
|
Choose TimesFM if
- You want the newest line: TimesFM 3.0 is dated 2026-08
- The work is research, where the non-commercial 3.0 license is fine
- Commercial use of versions 1.0 to 2.5 under Apache 2.0 is enough for you
Choose Chronos if
- Forecasts must account for promotions, prices and weather: Chronos-2 does
- You want the whole line under Apache 2.0 with no per-version caveats
- Resources are tight: Chronos has models from 8M
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
- Whisper or GigaAM: which to choose for business
- Whisper or Parakeet: which to choose for business
- Silero or Piper: which to choose for business
- FLUX or Stable Diffusion: which to choose for business
- FLUX or Qwen-Image: which to choose for business
- PaddleOCR-VL or DeepSeek-OCR: which to choose for business
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