About this app
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.
Install with Winget
Command line
PS> winget install --id imonoonoko.BitLlama -e
Official manifest sources
External links ↗
Downloads for version 0.16.0
| Installer | Details | SHA-256 | Download |
|---|---|---|---|
| x64 github.com | portable |
C8E7AAF01655D0342241C613181EFAF9A430EC19FC558BE9CA639394A3D9BE27
|
Download |
Version archive