compare
Ollama vs Xinference
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | Ollama | Xinference |
|---|---|---|
| Language | Go | Python |
| Licence | MIT | Apache-2.0 |
| Stars | 182k | 9.6k |
| Latest | v0.35.1 | v3.5.0 |
| Last push | 2026-10-06 | 2026-10-06 |
| Release cadence | about 4 days between releases | about 15 days between releases |
| Active contributors | 18 commit authors on the default branch in the last 90 days | 38 commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace ChatGPT. Alternatives to ChatGPT →
PartialOllamaRuns open-weight models on your own machine behind a local API. Pair it with a chat app for the interface.
PartialXinferenceServes open-weight language, embedding and speech models behind an OpenAI-compatible API.
Ollama
- v0.40.0-rc62026-09-25v0.40.0pre-release
- v0.35.12026-09-29Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone.
- v0.35.02026-09-28Ollama now supports decision models through /v1/systemone, based on TypeSafe’s Jev API.
- v0.34.42026-09-23Structured outputs on thinking models now apply in a single pass, making them faster and more reliable.
- v0.34.32026-09-19GET /api/show now advertises each model's thinking controls and default:
Xinference
Ollama
✓ signed The latest release, v0.35.1, carries a signature GitHub verified.
Loading the security report
Xinference
✓ signed The latest release, v3.5.0, carries a signature GitHub verified.
Loading the security report