| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| latest.json | 2026-07-14 | 2.5 kB | |
| Atomic.Chat_1.1.154_x64-setup.exe.sig | 2026-07-14 | 424 Bytes | |
| Atomic.Chat_1.1.154_x64_en-US.msi | 2026-07-14 | 116.8 MB | |
| Atomic.Chat_1.1.154_x64-setup.exe | 2026-07-14 | 78.3 MB | |
| Atomic.Chat.app.tar.gz | 2026-07-14 | 368.5 MB | |
| Atomic.Chat_1.1.154_universal.dmg | 2026-07-14 | 365.6 MB | |
| atomic-chat-mac-universal-1.1.154.zip | 2026-07-14 | 364.7 MB | |
| Atomic.Chat_1.1.154_amd64.AppImage.sig | 2026-07-14 | 428 Bytes | |
| Atomic.Chat_1.1.154_amd64.AppImage | 2026-07-14 | 210.0 MB | |
| Atomic Chat v1.1.154 source code.tar.gz | 2026-07-14 | 235.3 MB | |
| Atomic Chat v1.1.154 source code.zip | 2026-07-14 | 236.3 MB | |
| README.md | 2026-07-14 | 1.1 kB | |
| Totals: 12 Items | 2.0 GB | 5 | |
🚀 New Features
- Speculative decoding stats in the UI: token speed footer now shows tok/sec plus draft token acceptance %
đź”§ Improvements & Fixes
- Windows DLL bundling: all upstream DLLs now ship together, backend prefs for TurboQuant vs upstream no longer overwrite each other (#175)
- Resumable downloads: model downloads now survive interruptions, resuming from the last saved byte via HTTP Range requests with exponential backoff (1s to 32s) instead of starting over
- Faster, safer MLX loads: text only checkpoints route through proper model classification, with a dedicated lock so a slow or failed load no longer blocks other models
- Backend version checks on Windows no longer pop a console window
- 5+ stability/UI fixes across model loading, downloads, and token timing
🙏 Contributors
Thanks to @Vect0rM, @AlexFromAtomic, @TheLeaderDev, @dtorey-d for their contributions to this release!