Peer-to-peer distributed AI inference using 1-bit quantized models. CPU-only, 70-82% energy savings, 103+ tokens/sec. Validated on Zen 4 & Zen 5 (+35% cross-gen improvement).
-
Updated
Apr 27, 2026 - Python
#
1-bit-llm
Here are 4 public repositories matching this topic...
Windows-native BitNet and ternary LLM inference with CPU GGUF, GPU runtime, terminal and browser chat, and release zips.
windows cuda pytorch quantization bitnet fastapi llama-cpp local-llm llm-inference gguf 1-bit-llm ternary-llm falcon3
-
Updated
Mar 20, 2026 - Python
High-performance hybrid architecture for Agent Zero & BitNet b1.58. Natively optimized for Windows ARM64 (Snapdragon X Elite / Copilot+ PCs) using raw C++ inference and Docker-based agent orchestration.
-
Updated
Feb 6, 2026 - Python
Desktop chat app for Microsoft's 1-bit BitNet LLMs. Windows-native, CPU-only, zero dependencies
desktop-app windows chat-ui 1-bit pywebview bitnet openai-api cpu-inference llm openai-api-chatbot llama-cpp local-llm 1-bit-llm microsoft-bitnet
-
Updated
Apr 14, 2026 - Python
Improve this page
Add a description, image, and links to the 1-bit-llm topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the 1-bit-llm topic, visit your repo's landing page and select "manage topics."