compare
llama.cpp vs Xinference
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | llama.cpp | Xinference |
|---|---|---|
| Language | C++ | Python |
| Licence | MIT | Apache-2.0 |
| Stars | 130k | 9.6k |
| Latest | v0.6.0 | v3.5.0 |
| Last push | 2026-10-06 | 2026-10-06 |
| Release cadence | too few releases | about 15 days between releases |
| Active contributors | 173+ 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 →
Partialllama.cppRuns open-weight models on CPU or GPU, with a built-in server and a minimal web chat.
PartialXinferenceServes open-weight language, embedding and speech models behind an OpenAI-compatible API.
llama.cpp
- b114452026-10-06vulkan : check for null vkEnumerateInstanceVersion (#29872)pre-release
- b114432026-10-06models : consolidate nextn row cropping into shared helpers (#30017)pre-release
- b114402026-10-06llama : re-reserve the sched when the nextn extraction flags change (#30020)pre-release
- b114392026-10-06ggml: refactor selective expert copying to user code (#29943)pre-release
- b114382026-10-06test-llama-archs : initialize backends before generating models (#30034)pre-release
Xinference
llama.cpp
unsigned The latest release, v0.6.0, carries no signature GitHub could verify.
Loading the security report
Xinference
✓ signed The latest release, v3.5.0, carries a signature GitHub verified.
Loading the security report