Baixar Lemonade Server 11.7.0 per a Windows

Headline
- A new POST /v1/models/register endpoint registers or updates user.* model definitions without downloading any files.
- New GET/POST/DELETE /v1/models/{id}/options endpoints save, inspect, and reset per-model recipe options without loading the model, with per-load transient overrides.
- New GET /v1/stats and Prometheus /metrics endpoints report prefix-cache effectiveness and router route-switch counters.
- The built-in catalog adds the Qwen3.8-27B and NVIDIA Nemotron 3.5 Lightning 30B-A3B GGUF models and the Z-Image-Turbo image model.
- Lemonade can now be installed on Windows with winget and on macOS with a Homebrew cask.
Breaking Changes
- POST /pull now returns 400 and registers nothing when a model definition names an unservable or contradictory deployment mode; such labels are no longer silently normalized.
- Stored user_models.json entries that violate the new deployment-mode label rule are now skipped at startup with an error instead of being repaired.
- Removed the deprecated Lite Collection and Ultra Collection model registry entries.
- /v1/audio/transcriptions now returns raw text bodies for text/srt/vtt instead of a JSON {text: ...} wrapper, and returns 400 for unsupported response_format values.
- The TheNoise image backend no longer accepts per-request upscale and lora_dir recipe options; lora_dir is now set server-wide in config.json and upscale is only honored as a passed-through request parameter.
- lemonade launch opencode now emits a limit object (limit.context/limit.output) instead of a top-level contextWindow field.
- The no_broadcast config key is replaced by an inverted broadcast boolean, auto-migrated on load.
- An existing but unreadable extra_models_dir now returns 400 on /internal/set instead of being silently applied.
Lemonade Server

| Operating System | Downloads |
| ------------------ | ----------------------------------------- |
| Windows | lemonade.msi |
| Ubuntu 24.04+ | Launchpad PPA |
| Debian 13 (x86_64) | lemonade-server_11.7.0-debian13_amd64.deb |
| Debian 13 (ARM64) | lemonade-server_11.7.0-debian13_arm64.deb |
| Fedora 43 (x86_64) | lemonade-server-11.7.0-fc43.x86_64.rpm |
| Fedora 43 (ARM64) | lemonade-server-11.7.0-fc43.aarch64.rpm |
| Fedora 44 (x86_64) | lemonade-server-11.7.0-fc44.x86_64.rpm |
| Fedora 44 (ARM64) | lemonade-server-11.7.0-fc44.aarch64.rpm |
| macOS | Lemonade-11.7.0-Darwin.pkg |

Other platforms? See our Installation Options for Docker, Snap, Arch, Debian, and more.
Embeddable Lemonade
Portable binaries for bundling into your own installer. Run lemond ./ as a subprocess.

| Platform | Download |
| ------------ | ---------------------------------------------- |
| Ubuntu x64 | lemonade-embeddable-11.7.0-ubuntu-x64.tar.gz |
| Ubuntu arm64 | lemonade-embeddable-11.7.0-ubuntu-arm64.tar.gz |
| Windows x64 | lemonade-embeddable-11.7.0-windows-x64.zip |
| macOS arm64 | lemonade-embeddable-11.7.0-macos-arm64.tar.gz |

What's Changed
Thanks @SlawomirNowaczyk, @abn, @anditherobot, @bitgamma, @blackdeathdrow, @bong-water-water-bong, @fl0rianr, @ianbmacdonald, @iswaryaalex, @jeremyfowers, @kenvandine, @mzyy94, @osimarr, @popey, @ramkrishna2910, @superm1, @yelliver, @zaneni6 for your awesome contributions to this release!
Click to expand changelog
- Bump TheNoise to version v0.1.2 by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3079
- docs(backends): drop the model catalog tables from the backend reference by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3103
- fix(alias): report the real reason for alias validation failures by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3111
- feat(server): add model registration endpoint by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3118
- Debian packaging improvements by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3039
- docs: add winget and Homebrew install to homepage quickstart by @yelliver in https://github.com/lemonade-sdk/lemonade/pull/2970
- Trigger snap release candidate build from release branches by @kenvandine in https://github.com/lemonade-sdk/lemonade/pull/2908
- fix(server): compare artifacts, not commit SHAs, when checking for model updates by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/3073
- fix(server): normalize thinking controls for llama.cpp by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3132
- fix: stop request during prefill now possible by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3133
- ci: stop building unused targets in the validate workflows by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3052
- fix(server): harden extra models directory handling by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3105
- Fix #1833: Improve transcription response format compatibility by @anditherobot in https://github.com/lemonade-sdk/lemonade/pull/2088
- ci: stop pinning lite validation legs to the 128gb runner by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3139
- feat(models): add an explicit chat label by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3099
- feat(telemetry): capture prefix-cache effectiveness (cache_n, cached_tokens) and route-switch counts by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/2968
- Update FLM version by @zaneni6 in https://github.com/lemonade-sdk/lemonade/pull/3144
- Backend Battle Nightly Regression by @iswaryaalex in https://github.com/lemonade-sdk/lemonade/pull/3069
- Remove emoji from FAQ title by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3154
- Manage per-model recipe options without loading by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3110
- Enable % used context on opencode side panel by @osimarr in https://github.com/lemonade-sdk/lemonade/pull/1725
- feat(server,cli): add discovery and broadcast controls with config decoupling by @abn in https://github.com/lemonade-sdk/lemonade/pull/3135
- fix(packaging): add AppStream MetaInfo files for desktop entries by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3123
- fix(flm): correctly report downloaded model size by @mzyy94 in https://github.com/lemonade-sdk/lemonade/pull/3166
- Minor refactor of new gate code by @SlawomirNowaczyk in https://github.com/lemonade-sdk/lemonade/pull/2971
- update TheNoise v0.2.1 by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3171
- fix(flm): stop re-pulling already-downloaded models on every load by @mzyy94 in https://github.com/lemonade-sdk/lemonade/pull/3167
- feat: flag comment slop in a pre-commit rule, and run pre-commit in CI by @ianbmacdonald in https://github.com/lemonade-sdk/lemonade/pull/2689
- add lemonade version to benchmark results by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3173
- feat(server): support transient null overrides on load by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3172
- fix(macos): reduce log directory permissions to prevent privilege esc… by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/2625
- docs: add pull request template by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2551
- fix(npu): pre-reject NPU loads when auto-tune can only reserve fallback ctx (#1151) by @bong-water-water-bong in https://github.com/lemonade-sdk/lemonade/pull/3164
- models: add Qwen3.8 and Nemotron 3.5 GGUF by @yelliver in https://github.com/lemonade-sdk/lemonade/pull/3177
- Fix pre-commit JSON validation issues by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3179
- docs: fix multi-file checkpoint rendering by @yelliver in https://github.com/lemonade-sdk/lemonade/pull/3174
- Remove some MTP default flags by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3187
- ci: wire server eviction tests into CI by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3015
- ci: run watchdog lifecycle tests in backend CI by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3021
- test: replace Python system info replicas with C++ coverage by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3020
- fix(server): let load args override saved args by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3204
- refactor(server): drop load_command from the options endpoint by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3199
- fix(test): new watchdog test concurrency issue by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3201
- fix(pre-commit): make comment-slop runnable on Windows by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/3208
- Update to ROCm 7.14 by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/2768
- Fix stale gfx90X-dcgpu TheRock URL mapping for gfx908/gfx90a by @kenvandine in https://github.com/lemonade-sdk/lemonade/pull/3196
- test: add concurrent chat completion coverage by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2060
- Fail startup when one resolved address cannot bind by @popey in https://github.com/lemonade-sdk/lemonade/pull/3197
- fix(ci): resolve test flakes across C++ store, python test harness, and workflows by @abn in https://github.com/lemonade-sdk/lemonade/pull/2805
New Contributors
- @yelliver made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/2970
- @zaneni6 made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/3144
- @mzyy94 made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/3166
Full Changelog: https://github.com/lemonade-sdk/lemonade/compare/v11.6.0...v11.7.0

Windows installers are signed. Free code signing provided by SignPath.io, certificate by SignPath Foundation. See our Code Signing Policy.