Desktop GUI for BitLlama LLM inference engine with Soul learning and model management
BitLlama Desktop is a Tauri 2.0 + Svelte desktop application for local LLM inference.
Features include streaming chat, model browser with download, Soul learning (drag & drop,
correction learning), TTT adaptive inference, hardware auto-detection, and i18n (EN/JP).
v1.0.0 — Final Release
BitLlama v1.0.0. Development complete.
What is BitLlama?
A Pure Rust LLM inference engine with Soul learning and hierarchical memory.
- 7 model architectures: Llama-2/3, Gemma-2/3, Qwen2.5, Mistral, BitNet
- Soul learning: LoRA fine-tuning from conversations
- Memory system: 4-layer hierarchical memory + 7-stage Sleep consolidation
- Desktop GUI: Tauri 2.0 + Svelte 5, Japanese/English i18n
- Performance: 45.4 tok/s (7B), 90% of llama.cpp
- 1121 tests, quality score 9.0/10
Changes since v0.16.0
- CJK memory search fix (character bigram fallback for Japanese queries)
- Soul learning tests (warmup, chat template, VRAM guard)
- Chat template application fix for GGUF tokenizer fallback
- README/ROADMAP updated to reflect project completion
Install
Homebrew
brew tap imonoonoko/bitllama && brew install bitllama
winget
winget install imonoonoko.BitLlama
Or download binaries below
Built with Rust by @imonoonoko
Full Changelog: v0.16.0...v1.0.0
| Publisher | imonoonoko |
|---|---|
| Version | 1.0.0 |
| Release date | 2026-02-18 |
| License | MIT |
| Installer type | nullsoft |
| Architecture | x86 |
| Package ID | imonoonoko.BitLlamaDesktop |
| Install scope | Current user |
winget install --id=imonoonoko.BitLlamaDesktop -ewinget upgrade --id=imonoonoko.BitLlamaDesktop -ewinget uninstall --id=imonoonoko.BitLlamaDesktop -e"BitLlama-Desktop-Setup.exe" /SFull Changelog: v0.15.0...v0.16.0
Yes. BitLlama Desktop is free and open-source software released under the MIT license.
The latest version is 1.0.0, released on Feb 18, 2026.
The download button links to the official installer published on github.com, the same file Windows Package Manager installs. You can verify the downloaded file by comparing its SHA-256 checksum with 7cd1b5dc5f0d94c655561b7548f5354d9ba810a571c4b5773cd2616b3acba54b.
BitLlama Desktop runs on Windows and is available for 32-bit (x86) systems.
Run the offline installer with "BitLlama-Desktop-Setup.exe" /S, or install it with Windows Package Manager: winget install --id=imonoonoko.BitLlamaDesktop -e --silent.
Open Settings › Apps › Installed apps, find BitLlama Desktop and select Uninstall. From the command line, run winget uninstall --id=imonoonoko.BitLlamaDesktop -e.
Other AI for Productivity programs for Windows from different developers.
Foundry Local enables local execution of Small Language Models using the hardware on your device.
Standalone Docker Model Runner - run local AI models with no Docker Desktop or Engine required.
The first desktop app to run and train AI models locally.
Manage local AI models across supported inference engines.
Ship 100x With The Agent IDE
Codex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.