Download Latest Version
lemonade-embeddable-11.8.1-windows-x64.zip (5.3 MB)
Get an email when there's a new version of Lemonade
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| lemonade-embeddable-11.8.0-macos-arm64.tar.gz | 2026-08-26 | 5.6 MB | |
| lemonade-embeddable-11.8.0-ubuntu-arm64.tar.gz | 2026-08-26 | 6.7 MB | |
| lemonade-embeddable-11.8.0-ubuntu-x64.tar.gz | 2026-08-26 | 7.3 MB | |
| lemonade-embeddable-11.8.0-windows-x64.zip | 2026-08-26 | 5.3 MB | |
| lemonade-server-minimal.msi | 2026-08-26 | 7.0 MB | |
| lemonade.msi | 2026-08-26 | 10.7 MB | |
| README.md | 2026-08-26 | 13.7 kB | |
| v11.8.0 source code.tar.gz | 2026-08-26 | 4.3 MB | |
| v11.8.0 source code.zip | 2026-08-26 | 4.8 MB | |
| Totals: 9 Items | 51.9 MB | 2 | |
Headline
- A new experimental
ds4(DwarfStar) backend serves DeepSeek V4 Flash on AMD Strix Halo GPUs. - The catalog adds the RPG-HaloTales-V2 chat model, Flux-2-Klein-4B/9B image models, and new OpenMOSS voice-design and sound-effect speech models.
- Cloud providers now support custom authentication headers and byte-for-byte Anthropic Messages passthrough via
wire_format, andlemonade cloud list --jsonreports provider readiness. - Interrupted model downloads can be cancelled with Ctrl+C and resumed, capped with a new
download_rate_limitconfig key, and long connections stay alive through TCP keepalive and streaming heartbeats. - The new
lemonade update-modelscommand and global and per-model auto-update settings keep installed models current.
Breaking Changes
LemonadeServer.exe --portand--hostare now ephemeral in-memory overrides and no longer persist toconfig.json; uselemonade config set port=<P>/host=<H>to persist them.- Custom
*_argsprecedence changed: explicit request*_argsno longer inherit model/architecture args, andmerge_args=falsenow suppresses all inherited backend/machine args and overridable runtime defaults. - The llama.cpp backend now defaults
--parallelto 1, removing implicit multi-slot concurrent batching; restore it with--llamacpp-args "--parallel N". - Legacy telemetry attributes
openinference.session.idandopeninference.user.idwere removed in favor of the standardsession.idanduser.idkeys; update downstream dashboards and queries. - whisper.cpp transcription now defaults an omitted
languagetoauto(source-language auto-detection) instead of English; passlanguage=ento force English. - Removed the undocumented HTTP routes
/v1/params,/v1/log-level,/api/v1/test, and/status; use/internal/setand/internal/configinstead. - Backend
latestversion resolution now includes pre-releases for all backends.
Lemonade Server
| Operating System | Downloads |
|---|---|
| Windows | lemonade.msi (github.com) |
| Ubuntu 24.04+ | Launchpad PPA |
| Debian 13 (x86_64) | lemonade-server_11.8.0-debian13_amd64.deb (github.com) |
| Debian 13 (ARM64) | lemonade-server_11.8.0-debian13_arm64.deb (github.com) |
| Fedora 43 (x86_64) | lemonade-server-11.8.0-fc43.x86_64.rpm (github.com) |
| Fedora 43 (ARM64) | lemonade-server-11.8.0-fc43.aarch64.rpm (github.com) |
| Fedora 44 (x86_64) | lemonade-server-11.8.0-fc44.x86_64.rpm (github.com) |
| Fedora 44 (ARM64) | lemonade-server-11.8.0-fc44.aarch64.rpm (github.com) |
| macOS | Lemonade-11.8.0-Darwin.pkg (github.com) |
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-11.8.0-ubuntu-x64.tar.gz (github.com) |
| Ubuntu arm64 | lemonade-embeddable-11.8.0-ubuntu-arm64.tar.gz (github.com) |
| Windows x64 | lemonade-embeddable-11.8.0-windows-x64.zip (github.com) |
| macOS arm64 | lemonade-embeddable-11.8.0-macos-arm64.tar.gz (github.com) |
What's Changed
Thanks @Bekhouche, @GabrielReusRodriguez, @Geramy, @NineBallo, @abn, @anditherobot, @bitgamma, @blackdeathdrow, @bong-water-water-bong, @fl0rianr, @github-actions, @jeremyfowers, @jgmelber, @kenvandine, @meghsat, @original4422, @pwilkin, @ramkrishna2910, @sjjh, @soothill, @superm1, @zaneni6 for your awesome contributions to this release!
Click to expand changelog
* Add missing handler for lemonade:// URLs (Closes: [#1144656]) by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3195 * fix(GUI app): stop chat from bypassing collection.router routing by @meghsat in https://github.com/lemonade-sdk/lemonade/pull/3180 * Fix the developer setup page URLs by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3225 * fix(rocm): only stage amdhip64_7.dll when TheRock runtime is newer than System32 by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/3217 * docs: add latest release and Lemonade AI YouTube videos to news feed by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3202 * feat(cloud): configurable auth header name and prefix per provider by @jgmelber in https://github.com/lemonade-sdk/lemonade/pull/3222 * fix: cancel model download on Ctrl+C (SIGINT) via libcurl progress callback (#1385) by @bong-water-water-bong in https://github.com/lemonade-sdk/lemonade/pull/2462 * feat(server): record the backend launch command in /health by @anditherobot in https://github.com/lemonade-sdk/lemonade/pull/3229 * chore: rename app identifiers to ai.lemonadeserver namespace by @abn in https://github.com/lemonade-sdk/lemonade/pull/1978 * docs: add MCP Gateway to the API Spec nav by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3242 * Update the contribution guide for H2 2026 by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3246 * Add HaloTales-V2 and related models by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3264 * Flm version update by @zaneni6 in https://github.com/lemonade-sdk/lemonade/pull/3266 * fix(server): treat --port and --host CLI flags as ephemeral overrides by @abn in https://github.com/lemonade-sdk/lemonade/pull/3249 * Move persistent Lemonade JSON state from `.cache` to `.config` by @superm1 with @Copilot in https://github.com/lemonade-sdk/lemonade/pull/3028 * feat(server): hide backends with no runnable models on this host by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3219 * feat(telemetry): configurable session ID ingestion and OpenInference tool-call capture by @abn in https://github.com/lemonade-sdk/lemonade/pull/3248 * feat(server): treat config.json as sparse user overrides with deep merging by @abn in https://github.com/lemonade-sdk/lemonade/pull/3268 * test(telemetry): prevent dangling RuntimeConfig pointer and worker race in telemetry helpers test by @abn in https://github.com/lemonade-sdk/lemonade/pull/3283 * fix(server): resolve custom args by scope by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3265 * feat(server): enable cross-platform tcp keepalive socket options by @abn in https://github.com/lemonade-sdk/lemonade/pull/3209 * ci: temporarily disable tts-openmoss integration tests by @Geramy in https://github.com/lemonade-sdk/lemonade/pull/3291 * test: fix dangling CLI temp path in runtime override test by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3288 * test: move multi-checkpoint download-state coverage to C++ by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3286 * test: move llamacpp system backend policy coverage to C++ by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3287 * test: migrate model registry label validation to C++ by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3285 * feat(server): add context_length to the models endpoints by @anditherobot in https://github.com/lemonade-sdk/lemonade/pull/3280 * feat(cli): add --json output to lemonade cloud list by @GabrielReusRodriguez in https://github.com/lemonade-sdk/lemonade/pull/3261 * feat(streaming_proxy): add sse comment heartbeats during prompt prefill by @abn in https://github.com/lemonade-sdk/lemonade/pull/3210 * test(server): assert CLI parse return status and remove unused header in runtime override test by @abn in https://github.com/lemonade-sdk/lemonade/pull/3294 * fix(router): handle transient GPU hangs and compute errors in lemond by @abn in https://github.com/lemonade-sdk/lemonade/pull/2652 * feat(sync): add administrative model synchronization and auto-update configuration by @abn in https://github.com/lemonade-sdk/lemonade/pull/2779 * Update stable-diffusion.cpp to master-827-97d2990 and CUDA master-827-e2329c3 by @github-actions[bot] in https://github.com/lemonade-sdk/lemonade/pull/3311 * [Stable Diffusion] Respect the user configurable "Model Options" by @NineBallo in https://github.com/lemonade-sdk/lemonade/pull/2845 * Handle llama.cpp new release scheme by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3315 * Update faq.md: correcting list format by @sjjh in https://github.com/lemonade-sdk/lemonade/pull/3299 * fix(server): release large request memory by @soothill in https://github.com/lemonade-sdk/lemonade/pull/2873 * feat(server): size-filter streaming backends by working set, not full size by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3328 * docs: document POST /v1/install/dry-run by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3324 * feat(router): add min_total_chars / max_total_chars whole-conversation length conditions (#2958) by @meghsat in https://github.com/lemonade-sdk/lemonade/pull/3181 * docs: document POST /internal/simulate-vram-pressure by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3325 * feat(routing): add expected_output_tokens signal to RouteContext by @Bekhouche in https://github.com/lemonade-sdk/lemonade/pull/3163 * docs: document POST /v1/routing/validate by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3323 * Retire undocumented /params, /log-level, /api/v1/test, and /status routes by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3322 * Add TheNoise-based upscalers by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/3327 * Require 2 reviewers for breaking changes by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3348 * ci: retry apt-get on transient arm64 mirror 404s by @kenvandine in https://github.com/lemonade-sdk/lemonade/pull/3353 * fix(vllm): scale gpu-memory-utilization to free memory on shared-memory devices by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3344 * test(server): eliminate timing flakiness in StreamingHeartbeatTest by @abn in https://github.com/lemonade-sdk/lemonade/pull/3338 * fix(openmoss): bump OpenMOSS TTS pin to v0.3.0 and re-enable CI by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3335 * docs: add smart router subject area and two router maintainers by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3351 * Bump project version from 11.7.0 to 11.8.0 by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3354 * Update faq.md removed double tts chapter by @sjjh in https://github.com/lemonade-sdk/lemonade/pull/3300 * feat(cli): return per-model detail from status --json by @anditherobot in https://github.com/lemonade-sdk/lemonade/pull/3259 * fix(llamacpp): pin --parallel 1 so ctx_size is not oversubscribed by @jgmelber in https://github.com/lemonade-sdk/lemonade/pull/3277 * feat(config): add configurable download rate limit by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/3281 * fix(whisper): auto-detect omitted transcription language by @original4422 in https://github.com/lemonade-sdk/lemonade/pull/3245 * Feat/openmoss 0.3.0 backport/server side by @pwilkin in https://github.com/lemonade-sdk/lemonade/pull/2863 * feat(cloud): relay Anthropic-wire-format providers through /v1/messages by @jgmelber in https://github.com/lemonade-sdk/lemonade/pull/3223 * feat(backends): ds4 (DwarfStar) backend for DeepSeek V4 Flash [experimental] by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3047New Contributors
- @jgmelber made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/3222
- @sjjh made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/3299
- @soothill made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/2873
- @original4422 made their first contribution in https://github.com/lemonade-sdk/lemonade/pull/3245
Full Changelog: https://github.com/lemonade-sdk/lemonade/compare/v11.7.0...v11.8.0
Windows installers are signed. Free code signing provided by SignPath.io, certificate by SignPath Foundation. See our Code Signing Policy.
