lemonade-sdk/lemonade v2026.46.2 on GitHub

Headline

Container backends are now supported! Learn more: https://youtu.be/zfFuFRdyWgg
Adds the Halogen container backend and 5 containers from Strix Halo Toolboxes: Gufo, strix-llama.cpp, nathanw, rocmfpx, and DwarfStar4.
Benchmark results can now be submitted from lemonade bench to the public leaderboard with a single --submit flag, and a claim link lets others verify your setup.
New classification and decision-model capabilities: zero-shot text classification via POST /v1/classify with a labels parameter, and SystemOne decision models for typed, image-based, or score-based questions.
CUDA support added to TheNoise image generation engine.

Breaking Changes

The native backend for DwarfStar4 has been replaced by the container backend.
image_defaults and audio_defaults are no longer returned in the /models API response; their values are now nested under recipe_options, so clients reading the old keys will find them absent.
A new user_configurable boolean flag on backend descriptor options may expose technical knobs such as soft_pixel_cap, pcm_sample_rate, and pcm_channels to users — filter on this flag to hide internal settings.
FLM v1.0.11 returns max_tokens exactly as requested rather than max_tokens+1, so chat completions that relied on the extra token will now stop one token early.
FLM v1.0.11 streams token usage counts only when stream_options.include_usage is set; without it, the /api/v1/stats endpoint records no token counts or throughput for FLM streams.
FLM v1.0.11 returns 400 for previously-accepted invalid fields including invalid tool_choice, forced tool calls on small Qwen3 models (up to 1.7B), conversation history on *-flash models, and requests with no messages or prompt.

Lemonade Server

Operating System	Downloads
Windows	lemonade.msi
Ubuntu 24.04+	Launchpad PPA
Debian 13 (x86_64)	lemonade-server_2026.46.2-debian13_amd64.deb
Debian 13 (ARM64)	lemonade-server_2026.46.2-debian13_arm64.deb
Fedora 43 (x86_64)	lemonade-server-2026.46.2-fc43.x86_64.rpm
Fedora 43 (ARM64)	lemonade-server-2026.46.2-fc43.aarch64.rpm
Fedora 44 (x86_64)	lemonade-server-2026.46.2-fc44.x86_64.rpm
Fedora 44 (ARM64)	lemonade-server-2026.46.2-fc44.aarch64.rpm
macOS	Lemonade-2026.46.2-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-2026.46.2-ubuntu-x64.tar.gz
Ubuntu arm64	lemonade-embeddable-2026.46.2-ubuntu-arm64.tar.gz
Windows x64	lemonade-embeddable-2026.46.2-windows-x64.zip
macOS arm64	lemonade-embeddable-2026.46.2-macos-arm64.tar.gz

What's Changed

Thanks @Zorro-Zhang, @bitgamma, @fl0rianr, @iswaryaalex, @jeremyfowers, @kenvandine, @meghsat, @mike2307, @pwilkin for your awesome contributions to this release!

Click to expand changelog

add --submit/--submit-file to bench by @bitgamma in #3284
fix(gui): missing translation gaps by @fl0rianr in #3990
fix(app): use server sync for individual and bulk model updates by @fl0rianr in #3957
grabbing rocm versions per build by @iswaryaalex in #3996
fix(gui): show chat readiness and automatic backend install progress by @fl0rianr in #3992
Adding zero-shot classifier support by @meghsat in #3952
feat(backends): add TheNoise CUDA support by @fl0rianr in #4001
fix(app): support Firefox chatbot sidebar prompts by @fl0rianr in #3973
fix(gui3): Chat showing the wrong model after loading one from the Models tab (issue #4011) by @meghsat in #4013
fix(server): add missing backend args by @fl0rianr in #4021
fix(server): Turning off saved chats will retain the already saved chat sessions by @meghsat in #4012
fix(gui3): honor saved ctx_size when loading custom models (#4019) by @mike2307 in #4020
fix(server): apply default_model_source to built-in model downloads by @Zorro-Zhang in #4002
fix(gui3): Fixed bugs in Model load banners by @meghsat in #4030
refactor(models): list every model file in server_models.json by @jeremyfowers in #4041
chore: bump pwilkin backend versions by @pwilkin in #3993
feat(images): support optional upscale factor for TheNoise by @fl0rianr in #4046
feat(backends): run container backends through ContainerManager, starting with llamacpp:nathanw by @jeremyfowers in #3709
feat(ds4): move ds4:rocm to a container backend by @jeremyfowers in #3710
feat(rocmfpx): add the ROCm FPX container backend by @jeremyfowers in #3711
feat(halogen): add the Halogen Flash container backend by @jeremyfowers in #3712
ci: keep container backend images on the newest build of their tags by @jeremyfowers in #3713
ci: Add cuda backend validation for llama.cpp on Linux using self-hosted amd64 and arm64 runners by @kenvandine in #3714
fix(gui): align chat toolbar controls (#4051) by @fl0rianr in #4053
feat(llamacpp): add the halobox container backend by @jeremyfowers in #4029
feat(gufo): add the Gufo container backend by @jeremyfowers in #4031
Add SystemOne decision models: /v1/systemone, GGUF zero-shot on /v1/classify, and the systemone router classifier by @meghsat in #3956
Remove image_defaults and audio_defaults by @bitgamma in #4049

New Contributors

@Zorro-Zhang made their first contribution in #4002

Full Changelog: v2026.45.3...v2026.46.2

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