SelfHostMap

TextGen (text-generation-webui) vs Xinference

Short answer

TextGen (text-generation-webui): Local LLM app (formerly text-generation-webui) with a browser UI, OpenAI/Anthropic-compatible API and LoRA training. Xinference: Model-serving platform for LLM, embedding, rerank, speech and image models behind one OpenAI-compatible API. Both are in our Local model runtimes category.

Choose TextGen (text-generation-webui) if you want: larger community (47.7k vs 9.6k GitHub stars).

Choose Xinference if you want: fewer license conditions (Permissive vs Network copyleft (AGPL)) and simpler deploy (one container vs a multi-container stack).

TextGen (text-generation-webui) and Xinference publish no official RAM figure, so we cannot compare hosting cost directly.

Last updated · computed from each project's official docs and live GitHub data · sources

TextGen (text-generation-webui) vs Xinference side by side

TextGen (text-generation-webui)Xinference
CategoryLocal model runtimesLocal model runtimes
What it isLocal LLM app (formerly text-generation-webui) with a browser UI, OpenAI/Anthropic-compatible API and LoRA training.Model-serving platform for LLM, embedding, rerank, speech and image models behind one OpenAI-compatible API.
LicenseAGPL-3.0Apache-2.0
License typeNetwork copyleft (AGPL)Permissive
License conditionsFree for internal and commercial use. If you modify TextGen and let users interact with it over a network, you must offer them the modified source under AGPL-3.0. Models have their own licenses.Permissive. Internal and commercial use allowed; keep the Apache-2.0 license and notices. Xinference Enterprise is a separate commercial edition. Models keep their own licenses.
StatusActiveActive
GitHub stars47.7k9.6k
Last commitAug 17, 2026Oct 30, 2026
Latest releasev4.9v4.1.0
Minimum hardwareNot publishedNot published
Recommended hardwareNot publishedNot published
RAM measured by usNot tested yetNot tested yet
GPUOptional. Docker variants exist for NVIDIA, AMD, Intel Arc (beta) and CPU-only inference; portable builds come in CUDA, Vulkan, ROCm and CPU-only versions.The default Docker image requires an NVIDIA GPU (host CUDA 13.0 or newer, driver 580 or newer, NVIDIA Container Toolkit). For CPU, use the image tag with a -cpu suffix; pip installs on Apple Silicon can use the MLX engine.
Est. server costNot estimatedNot estimated
Deploy methodDocker Compose (built locally from the repo)Docker
Known gotchas4 listed4 listed
TelemetryNone (documented)Not documented
Calls home by defaultNo (documented)Yes, by default
SSO (OIDC / SAML / LDAP)Not documentedFree (OIDC free)
Audit logNot documentedYes, free
RBACNot documentedYes, free
DetailsFull TextGen (text-generation-webui) guide →Full Xinference guide →

Key differences

  • License: TextGen (text-generation-webui): AGPL-3.0 (Network copyleft (AGPL)). Xinference: Apache-2.0 (Permissive).
  • Deploy: TextGen (text-generation-webui): Docker Compose (built locally from the repo) · multi-container stack. Xinference: Docker · single container.
  • GitHub stars: TextGen (text-generation-webui): 47.7k. Xinference: 9.6k.
  • Last commit: TextGen (text-generation-webui): Aug 17, 2026. Xinference: Oct 30, 2026.
  • Latest release: TextGen (text-generation-webui): v4.9 (May 20, 2026). Xinference: v4.1.0 (Oct 25, 2026).

Same for both: Category: Local model runtimes; Official hardware: not published; GPU: optional / see notes; Est. server cost: not estimated (no official RAM figure); Status: Active.

TextGen (text-generation-webui) vs Xinference: FAQ

TextGen (text-generation-webui) or Xinference: which should a small business choose?

Choose TextGen (text-generation-webui) if you want: larger community (47.7k vs 9.6k GitHub stars). Choose Xinference if you want: fewer license conditions (Permissive vs Network copyleft (AGPL)) and simpler deploy (one container vs a multi-container stack). TextGen (text-generation-webui) and Xinference publish no official RAM figure, so we cannot compare hosting cost directly.

Which is cheaper to self-host, TextGen (text-generation-webui) or Xinference?

TextGen (text-generation-webui): not estimated (no official RAM figure). Xinference: not estimated (no official RAM figure). Our estimate is the cheapest Hetzner Cloud plan that meets each project's official RAM and vCPU figure; it covers the server only.

How much hardware do TextGen (text-generation-webui) and Xinference need?

TextGen (text-generation-webui): not published. Xinference: not published.

What is the license difference between TextGen (text-generation-webui) and Xinference?

TextGen (text-generation-webui): AGPL-3.0 (Network copyleft (AGPL)). Free for internal and commercial use. If you modify TextGen and let users interact with it over a network, you must offer them the modified source under AGPL-3.0. Models have their own licenses. Xinference: Apache-2.0 (Permissive). Permissive. Internal and commercial use allowed; keep the Apache-2.0 license and notices. Xinference Enterprise is a separate commercial edition. Models keep their own licenses. This is a summary, not legal advice.

Is TextGen (text-generation-webui) or Xinference more actively maintained?

TextGen (text-generation-webui): Active, last commit Aug 17, 2026. Xinference: Active, last commit Oct 30, 2026. GitHub data refreshed Oct 30, 2026.

Which is easier to deploy, TextGen (text-generation-webui) or Xinference?

TextGen (text-generation-webui) installs via Docker Compose (built locally from the repo) (multi-container stack); Xinference via Docker (single container). TextGen (text-generation-webui) lists 4 known gotchas and Xinference lists 4; see each app page.

Related

Sources

Every value is generated from the same verified data as the app pages. Spotted something wrong? Tell us.