BitLlama

by imonoonokov1.0.0

Last updated Jul 15, 2026

Pure Rust LLM inference engine with 1.58-bit ternary support and Test-Time Training

Install with winget

$ winget install --id imonoonoko.BitLlama --exact --version 1.0.0

Run in Command Prompt, PowerShell, or Windows Terminal. Prompts for any agreements.

Built by Pckgr

For IT teams

Deploy this app to your whole fleet with Pckgr RMM.

App deployment, patching, and remote support in one place. Push this app to every device you manage, keep it patched automatically, and see new CVEs the moment they land. Works with Intune or fully standalone.

Free for up to 5 devices.

About

BitLlama is a Pure Rust LLM inference engine featuring 1.58-bit ternary quantization,

Test-Time Training (TTT), Soul learning system, MCP server/client, and private RAG.

Supports Llama, Gemma, Mistral, Qwen, and BitNet models.

OpenAI-compatible API server included.

Installers · v1.0.0

Architecture	Type	Scope	Install	Download
x64	Portable	-		Direct

Copy a command tailored to that specific architecture, type, and scope - useful when winget would otherwise pick a different default.

Security

No known CVEs for BitLlama.

Coverage is best-effort and depends on a winget package mapping to an NVD CPE entry. Absence here is not a guarantee of safety.

Related apps

BitLlama Desktopimonoonoko
imonoonoko.BitLlamaDesktopv1.0.0
Desktop GUI for BitLlama LLM inference engine with Soul learning and model management
O
Ollama (Portable)Ollama
Ollama.Ollama.Portablev0.20.2
Start building with open models.
Claude CodeAnthropic PBC
Anthropic.ClaudeCodev2.1.218
Unleash Claude’s raw power directly in your terminal. Search million-line codebases instantly. Turn hours-long workflows into a single command. Your tools. Your workflow. Your codebase, evolving at thought speed.
CursorAnysphere
Anysphere.Cursorv3.13.21
The AI Code Editor
P
PrismCatEtgpao
paopaoandlingyia.PrismCatv1.12.0
A self-hosted, transparent proxy and debugging console for LLM APIs.
R
rtkrtk-ai
rtk-ai.rtkv0.44.0
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

More from imonoonoko or browse ai, cli, inference.

Frequently asked questions

How do I install BitLlama on Windows?

Open Windows Terminal, PowerShell, or Command Prompt and run: winget install --id imonoonoko.BitLlama --exact --version 1.0.0. winget downloads the installer from imonoonoko and runs it. Requires Windows 10 (1809+) or Windows 11.

How do I install BitLlama silently for unattended deployment?

Add --silent and accept the agreements upfront: winget install --id imonoonoko.BitLlama --exact 1.0.0 --silent --accept-package-agreements --accept-source-agreements. This is the variant Intune, Configuration Manager, and other deployment tools should use.

How do I uninstall BitLlama via winget?

Run: winget uninstall --id imonoonoko.BitLlama --exact. Add --silent for unattended uninstalls. winget will use the registered uninstaller from BitLlama's Apps & Features entry.

Is BitLlama free?

BitLlama is distributed under MIT. Refer to the publisher (https://github.com/imonoonoko/Bit-TTT-Engine) for the full license terms - Wingetly itself does not charge for installation.

Does BitLlama work on Windows 10?

Yes, as long as your Windows 10 build supports winget (1809 or newer). winget ships with App Installer on Windows 10/11 and pulls BitLlama directly from the publisher.

How do I keep BitLlama up to date?

Run winget upgrade --id imonoonoko.BitLlama --exact, or winget upgrade --all to update everything winget tracks. We index 1 version of BitLlama from microsoft/winget-pkgs.