# Foundry Local vs TextGen (slim)

> Foundry Local scores 60.5 (C) on agent readiness against TextGen's 45.1 (E), and leads in 4 of 7 scored categories. TextGen leads on schema & documentation. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/foundry-local-vs-text-generation-webui.md (~2,650 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/foundry-local-vs-text-generation-webui.json · canonical https://www.anchorterminal.com/compare/foundry-local-vs-text-generation-webui
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Foundry Local scores 60.5 (C) on agent readiness against TextGen's 45.1 (E), and leads in 4 of 7 scored categories. TextGen leads on schema & documentation. Both do local inference.

- Foundry Local: C 60.5, rank #461 of 842 · https://www.anchorterminal.com/tools/foundry-local.min.md
- TextGen: E 45.1, rank #775 of 842 · https://www.anchorterminal.com/tools/text-generation-webui.min.md
- Foundry Local, good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows. Ahead on Reliability, 68 against 51; Agent ergonomics, 61 against 50; Maintenance & community, 88 against 24; Transparency & trust, 72 against 49. Also No key needed to call it; No incidents deducted, where TextGen loses 4 points for them.
- TextGen, good for A person who wants one app for several backends (llama.cpp, ExLlamaV3, Transformers) with an OpenAI and Anthropic-compatible endpoint, LoRA training and image generation. Ahead on Schema & documentation, 61 against 53.

| Category | Foundry Local | TextGen |
| --- | --- | --- |
| Reliability (16%) | 68 | 51 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 53 | 61 |
| Agent ergonomics (13%) | 61 | 50 |
| Security & auth (14%) | 39 | 40 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 88 | 24 |
| Transparency & trust (7%) | 72 | 49 |

| Fact (where they differ) | Foundry Local | TextGen |
| --- | --- | --- |
| Kind | SDK + MCP | Model platform |
| Vendor | Microsoft | oobabooga |
| Auth | None | API key |
| Licence | MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own | AGPL-3.0 |
| Last release | 2026-09-29 | 2026-05-20 |
| Popularity | 2.6k stars, 105k npm/wk, 47k PyPI/wk | 48k stars |