Microsoft’s new large language model (LLM) puts significantly less strain on hardware than other LLMs—and it’s free to experiment with. The 1-bit LLM (1.58-bit, to be more precise) uses -1 ...

AMD Instinct MI350 details: 185 billion transistors, 3D multi-chiplet, up to 288GB of HBM3E memory, CoWoS-S advanced ...

Microsoft’s “1‑bit” AI model runs on a CPU only, while matching larger systems Future AI might not need supercomputers thanks to models like BitNet b1.58 2B4T.

Description (Brief) Intel 1103 1K Bit pMOS Dynamic Random Access Memory (DRAM) chip. Marked on top: "i / D1103 / I3261100", on bottom: "i Philippines / B / 7928". Refreshing all 1024 bits is ...

NVIDIA details its new Blackwell Ultra GB300: dual-die design with 208 billion transistors, up to 288GB HBM3E, made on TSMC N4P process node.

Understanding Memory An inside look at different memory types and how they work.

Home > Computing Microsoft's New Compact 1-Bit LLM Needs Just 400MB of Memory BitNet b1.58 2B4T is freely available to the public.