Download Latest Version Atomic.Chat_2.2.14_x64_en-US.msi (227.3 MB) Google Add to Preferred Sources
Home / v2.2.3
Name Modified Size InfoDownloads / Week
Parent folder
latest.json 2026-10-09 3.6 kB
Atomic.Chat_2.2.3_x64-setup.exe.sig 2026-10-09 424 Bytes
Atomic.Chat_2.2.3_x64_en-US.msi 2026-10-09 217.5 MB
Atomic.Chat_2.2.3_x64-setup.exe 2026-10-09 152.1 MB
Atomic.Chat.app.tar.gz 2026-10-09 559.2 MB
Atomic.Chat_2.2.3_universal.dmg 2026-10-09 552.3 MB
atomic-chat-mac-universal-2.2.3.zip 2026-10-09 551.6 MB
Atomic.Chat_2.2.3_arm64-setup.exe.sig 2026-10-09 424 Bytes
Atomic.Chat_2.2.3_arm64-setup.exe 2026-10-09 116.5 MB
Atomic.Chat_2.2.3_amd64.AppImage.sig 2026-10-09 424 Bytes
Atomic.Chat_2.2.3_amd64.AppImage 2026-10-09 328.1 MB
Atomic.Chat_2.2.3_aarch64.AppImage.sig 2026-10-09 428 Bytes
Atomic.Chat_2.2.3_aarch64.AppImage 2026-10-09 285.4 MB
Atomic Chat v2.2.3 source code.tar.gz 2026-10-09 238.9 MB
Atomic Chat v2.2.3 source code.zip 2026-10-09 241.8 MB
README.md 2026-10-09 1.9 kB
Totals: 16 Items   3.2 GB 11

🚀 New Features

  • Qwen-Image-2.1-Turbo support — you can now create, reference, and edit images with Qwen-Image-2.1-Turbo (same 7B family as Qwen-Image-2.1) with a 1024px default and its distilled sigma schedule included.

🔧 Improvements & Fixes

  • Core upgrade to atomic-chat-core 0.11.6→0.11.7 — fixes include a corrected sigma schedule closure so distilled runs finish without residual noise, img_gen now sends schedules required by Qwen-Image-2.1-Turbo, more resilient llama.cpp build selection, faster video decode on Apple Silicon (M1), and a WSL model-download fix.
  • retrieve and docs retrieval improved — file_ids now match by id or file name (case-insensitive and path-end), the system prompt tells models when documents are attached, and retrieve falls back to searching all documents when no exact match is found.
  • sends wait for web search activation — messages sent while Web Search is "Connecting" now wait up to 12s for the search tool to become available and warn if the message proceeds without search.
  • context indicator token counting fixed — the header now correctly counts tokens when only assistant turns are present and avoids empty requests that caused server errors.
  • toast dismissal bug fixed — overlapping "Starting Model" toasts no longer get stuck after a refused load.
  • CLI removed from Settings and startup — the app no longer offers or auto-installs the Atomic Chat CLI from Settings, while existing installs are still refreshed after updates.
  • app update UX improved — the Update button now shows download progress (and installation status), the downloads panel no longer lists the app-update row, and the installer flow displays accurate progress and messaging while preventing cancellation.

🙏 Contributors

Thanks to @Vect0rM for their contributions to this release!

Source: README.md, updated 2026-10-09