lemonade-sdk/lemonade candidate-v2026.43.1 on GitHub

Headline

GET /api/v1/system-stats selects the primary GPU by total memory instead of highest utilization, with NVIDIA GPU utilization and VRAM reporting, so the numbers match what you expect on multi-GPU systems.
Image editing now accepts one or more reference images with auto-selected output dimensions and a configurable soft pixel cap.
Live inference throughput is now available on GET /v1/stats as live.active_requests and live.estimated_tokens_per_second.
lemonade bench shows prefill throughput (PP t/s) in table output and --json, with --compare mode tracking PP change.

GET /api/v1/system-stats now reports the primary GPU by total memory instead of the GPU with highest utilization, so dashboard values and alerting thresholds may change on multi-GPU systems.
Models gated behind a guest-tier backend are now hidden from GET /v1/models?show_all=true and return model_not_supported on pull until the guest backend is installed.

Operating System	Downloads
Windows	lemonade.msi
Ubuntu 24.04+	Launchpad PPA
Debian 13 (x86_64)	lemonade-server_2026.43.1-debian13_amd64.deb
Debian 13 (ARM64)	lemonade-server_2026.43.1-debian13_arm64.deb
Fedora 43 (x86_64)	lemonade-server-2026.43.1-fc43.x86_64.rpm
Fedora 43 (ARM64)	lemonade-server-2026.43.1-fc43.aarch64.rpm
Fedora 44 (x86_64)	lemonade-server-2026.43.1-fc44.x86_64.rpm
Fedora 44 (ARM64)	lemonade-server-2026.43.1-fc44.aarch64.rpm
macOS	Lemonade-2026.43.1-Darwin.pkg

Other platforms? See our Installation Options for Docker, Snap, Arch, Debian, and more.

Portable binaries for bundling into your own installer. Run lemond ./ as a subprocess.

Platform	Download
Ubuntu x64	lemonade-embeddable-2026.43.1-ubuntu-x64.tar.gz
Ubuntu arm64	lemonade-embeddable-2026.43.1-ubuntu-arm64.tar.gz
Windows x64	lemonade-embeddable-2026.43.1-windows-x64.zip
macOS arm64	lemonade-embeddable-2026.43.1-macos-arm64.tar.gz

Thanks @bitgamma, @fl0rianr, @jeremyfowers, @joshuacox, @sreeram-11, @zaneni6 for your awesome contributions to this release!

Click to expand changelog

refactor(server): run backend servers through ServerProcess and NativeProcess by @jeremyfowers in #3705
fix(server): support multi-reference image editing by @fl0rianr in #3801
fix(config): read the distro defaults override from lemond's own install prefix by @jeremyfowers in #3775
feat(images): add per-model edit size caps and Qwen-Image-2.1 Turbo INT8 by @fl0rianr in #3803
fix(models): preserve catalog identities in extra_models_dir by @fl0rianr in #3805
fix(models): prevent duplicate discovery of incomplete shards by @fl0rianr in #3811
docs: add systemd start step to the Arch install page by @joshuacox in #3784
ci: bump auto-labeler to Claude Haiku 5.5 by @fl0rianr in #3774
feat(backends): label each backend with a tier and a format by @jeremyfowers in #3706
Update Lemonade to ROCm 10.1.0 by @sreeram-11 in #3821
chore(flm): bump FLM to v1.0.8 by @zaneni6 in #3810
Build cpp-httplib once instead of in every file that includes it by @jeremyfowers in #3837
fix(server): report NVIDIA GPU and VRAM usage by @fl0rianr in #3282
mark TheNoise as Core-tier by @bitgamma in #3826
test: pre-pull server_llm.py's models and cover implicit pull on inference by @jeremyfowers in #3839
lemonade bench: add prefill TPS by @bitgamma in #3759
Add AnythingLLM and Phoronix Lemonade 11.9 articles to news page by @jeremyfowers in #3836
fix(server): expose live inference throughput across backends by @fl0rianr in #3791
test: isolate every C++ test from the real config dir by @jeremyfowers in #3612

Full Changelog: v2026.42.1...candidate-v2026.43.1

The Windows installers in this release candidate are not signed; Windows SmartScreen will warn before installing. Stable releases are signed.