v3.5.1

mudler/LocalAIv3.5.1Sep 17, 2025by mudler
AI Summary

A significant update featuring the introduction of the LocalAI Launcher with a welcome page, support for the HuggingFace endpoint environment variable, and Whisper diarization. It also includes numerous bug fixes and adds over 15 new models to the gallery.
Key Highlights

Launcher welcome page feature introduced.
Added support for HF_ENDPOINT environment variable.
Whisper backend now supports diarization (tinydiarize).
Added numerous models: Hermes-4-14b, MiniCPM-V-4.5-8b, Baidu Ernie-4.5-21b, Holo 1.5 series, Alibaba Tongyi DeepResearch, Webwatcher, and Websailor series.
New Features

Launcher welcome page.
HF_ENDPOINT environment variable support.
Whisper diarization support.
New model gallery additions (Hermes-4, MiniCPM-V, Ernie-4.5, Holo, Tongyi, Webwatcher, Websailor).
Full Release Notes

<!-- Release notes generated using configuration in .github/release.yml at master -->

## What's Changed
### Bug fixes :bug:
* fix: make sure to turn down all processes on exit by @mudler in https://github.com/mudler/LocalAI/pull/6200
* fix(p2p): automatically install llama-cpp for p2p workers by @mudler in https://github.com/mudler/LocalAI/pull/6199
* Point to LocalAI-examples repo for llava by @mauromorales in https://github.com/mudler/LocalAI/pull/6241
* fix: runtime capability detection for backends by @sozercan in https://github.com/mudler/LocalAI/pull/6149
* fix(chat): use proper finish_reason for tool/function calling by @imkira in https://github.com/mudler/LocalAI/pull/6243
* fix(rocm): Rename tag suffix for hipblas whisper build to match backend config by @KingJ in https://github.com/mudler/LocalAI/pull/6247
* fix(llama-cpp): correctly calculate embeddings by @mudler in https://github.com/mudler/LocalAI/pull/6259
### Exciting New Features 🎉
* feat(launcher): show welcome page by @mudler in https://github.com/mudler/LocalAI/pull/6234
* feat: support HF_ENDPOINT env for the HuggingFace endpoint by @qxo in https://github.com/mudler/LocalAI/pull/6220
### 🧠 Models
* chore(model gallery): add nousresearch_hermes-4-14b by @mudler in https://github.com/mudler/LocalAI/pull/6197
* chore(model gallery): add MiniCPM-V-4.5-8b-q4_K_M by @M0Rf30 in https://github.com/mudler/LocalAI/pull/6205
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/6211
* feat(whisper): Add diarization (tinydiarize) by @richiejp in https://github.com/mudler/LocalAI/pull/6184
* chore(model gallery): add baidu_ernie-4.5-21b-a3b-thinking by @mudler in https://github.com/mudler/LocalAI/pull/6267
* chore(model gallery): add aquif-ai_aquif-3.5-8b-think by @mudler in https://github.com/mudler/LocalAI/pull/6269
* chore(model gallery): add qwen3-stargate-sg1-uncensored-abliterated-8b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/6270
* chore(model gallery): add k2-think-i1 by @mudler in https://github.com/mudler/LocalAI/pull/6288
* chore(model gallery): add holo1.5-72b by @mudler in https://github.com/mudler/LocalAI/pull/6289
* chore(model gallery): add holo1.5-7b by @mudler in https://github.com/mudler/LocalAI/pull/6290
* chore(model gallery): add holo1.5-3b by @mudler in https://github.com/mudler/LocalAI/pull/6291
* chore(model gallery): add alibaba-nlp_tongyi-deepresearch-30b-a3b by @mudler in https://github.com/mudler/LocalAI/pull/6295
* chore(model gallery): add webwatcher-7b by @mudler in https://github.com/mudler/LocalAI/pull/6297
* chore(model gallery): add webwatcher-32b by @mudler in https://github.com/mudler/LocalAI/pull/6298
* chore(model gallery): add websailor-32b by @mudler in https://github.com/mudler/LocalAI/pull/6299
* chore(model gallery): add websailor-7b by @mudler in https://github.com/mudler/LocalAI/pull/6300
### 📖 Documentation and examples
* chore(docs): add MacOS dmg download button by @mudler in https://github.com/mudler/LocalAI/pull/6233
### 👒 Dependencies
* chore(deps): bump github.com/opencontainers/image-spec from 1.1.0 to 1.1.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6223
* chore(deps): bump actions/stale from 9.1.0 to 10.0.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6227
* chore(deps): bump go.opentelemetry.io/otel/exporters/prometheus from 0.50.0 to 0.60.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6226
* chore(deps): bump oras.land/oras-go/v2 from 2.5.0 to 2.6.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6225
* chore(deps): bump github.com/swaggo/swag from 1.16.3 to 1.16.6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6222
* chore(deps): bump actions/labeler from 5 to 6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6229
* feat(nvidia-gpu): bump images to cuda 12.8 by @mudler in https://github.com/mudler/LocalAI/pull/6239
* feat(chatterbox): add MPS, and CPU, pin version by @mudler in https://github.com/mudler/LocalAI/pull/6242
### Other Changes
* chore: :arrow_up: Update ggml-org/llama.cpp to `0fce7a1248b74148c1eb0d368b7e18e8bcb96809` by @localai-bot in https://github.com/mudler/LocalAI/pull/6193
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `2eb3845df5675a71565d5a9e13b7bad0881fafcd` by @localai-bot in https://github.com/mudler/LocalAI/pull/6192
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/6201
* chore: :arrow_up: Update ggml-org/llama.cpp to `fb15d649ed14ab447eeab911e0c9d21e35fb243e` by @localai-bot in https://github.com/mudler/LocalAI/pull/6202
* Fix Typos in Docs by @alizfara112 in https://github.com/mudler/LocalAI/pull/6204
* chore: :arrow_up: Update ggml-org/whisper.cpp to `bb0e1fc60f26a707cabf724edcf7cfcab2a269b6` by @localai-bot in https://github.com/mudler/LocalAI/pull/6203
* chore: :arrow_up: Update ggml-org/llama.cpp to `408ff524b40baf4f51a81d42a9828200dd4fcb6b` by @localai-bot in https://github.com/mudler/LocalAI/pull/6207
* chore: :arrow_up: Update ggml-org/llama.cpp to `c4df49a42d396bdf7344501813e7de53bc9e7bb3` by @localai-bot in https://github.com/mudler/LocalAI/pull/6209
* chore: ⬆️ Update leejet/stable-diffusion.cpp to d7f430cd693f2e12ecbaa0ce881746cf305c3b1f by @richiejp in https://github.com/mudler/LocalAI/pull/6213
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `c648001030d4c2cc7c851fdaf509ee36d642dc99` by @localai-bot in https://github.com/mudler/LocalAI/pull/6215
* chore: :arrow_up: Update ggml-org/llama.cpp to `3976dfbe00f02a62c0deca32c46138e4f0ca81d8` by @localai-bot in https://github.com/mudler/LocalAI/pull/6214
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `abb115cd021fc2beed826604ed1a479b6a77671c` by @localai-bot in https://github.com/mudler/LocalAI/pull/6236
* chore: :arrow_up: Update ggml-org/whisper.cpp to `edea8a9c3cf0eb7676dcdb604991eb2f95c3d984` by @localai-bot in https://github.com/mudler/LocalAI/pull/6237
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `b0179181069254389ccad604e44f17a2c25b4094` by @localai-bot in https://github.com/mudler/LocalAI/pull/6246
* chore: :arrow_up: Update ggml-org/llama.cpp to `0e6ff0046f4a2983b2c77950aa75960fe4b4f0e2` by @localai-bot in https://github.com/mudler/LocalAI/pull/6235
* chore: ⬆️ Update leejet/stable-diffusion.cpp to fce6afcc6a3250a8e17923608922d2a99b339b47 by @richiejp in https://github.com/mudler/LocalAI/pull/6256
* chore: :arrow_up: Update ggml-org/llama.cpp to `40be51152d4dc2d47444a4ed378285139859895b` by @localai-bot in https://github.com/mudler/LocalAI/pull/6260
* chore: :arrow_up: Update ggml-org/llama.cpp to `aa0c461efe3603639af1a1defed2438d9c16ca0f` by @localai-bot in https://github.com/mudler/LocalAI/pull/6261
* chore(aio): upgrade minicpm-v model to latest 4.5 by @M0Rf30 in https://github.com/mudler/LocalAI/pull/6262
* chore: :arrow_up: Update ggml-org/llama.cpp to `0fa154e3502e940df914f03b41475a2b80b985b0` by @localai-bot in https://github.com/mudler/LocalAI/pull/6263
* chore: :arrow_up: Update ggml-org/llama.cpp to `6c019cb04e86e2dacfe62ce7666c64e9717dde1f` by @localai-bot in https://github.com/mudler/LocalAI/pull/6265
* chore: ⬆️ Update leejet/stable-diffusion.cpp to 0ebe6fe118f125665939b27c89f34ed38716bff8 by @richiejp in https://github.com/mudler/LocalAI/pull/6271
* chore: :arrow_up: Update ggml-org/llama.cpp to `b907255f4bd169b0dc7dca9553b4c54af5170865` by @localai-bot in https://github.com/mudler/LocalAI/pull/6287
* chore: :arrow_up: Update ggml-org/llama.cpp to `8ff206097c2bf3ca1c7aa95f9d6db779fc7bdd68` by @localai-bot in https://github.com/mudler/LocalAI/pull/6292

## New Contributors
* @alizfara112 made their first contribution in https://github.com/mudler/LocalAI/pull/6204
* @qxo made their first contribution in https://github.com/mudler/LocalAI/pull/6220
* @imkira made their first contribution in https://github.com/mudler/LocalAI/pull/6243
* @KingJ made their first contribution in https://github.com/mudler/LocalAI/pull/6247

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v3.5.0...v3.5.1