QuantBench
prajwalpujari16 · Kit
A browser studio for exploring LLM quantization below one byte per weight, with a Pareto frontier explorer, BitNet 1.58b bit-packing registers and a layer sens…
New
prajwalpujari16 · Kit
A browser studio for exploring LLM quantization below one byte per weight, with a Pareto frontier explorer, BitNet 1.58b bit-packing registers and a layer sens…
microsoft · Kit
Microsoft’s official inference framework for 1-bit LLMs, built on llama.cpp. It runs ternary models such as BitNet b1.58 on x86 and ARM CPUs, and has a GPU ker…