Live data from Hacker News

BitNet: Inference framework for 1-bit LLMs

github.com

1–10 of 179 posts

Re: BitNet: Inference framework for 1-bit LLMs

#6
The title is misleading — there's no trained 100B model, just an inference framework that claims to handle one. But the engineering is worth paying attention to. I run quantized 70B models locally (M2 Max 96GB, llama.cpp + LiteLLM), and memory bandwidth is always the bottleneck. The 1.58-bit approach is interesting because ternary weights turn matmuls into additions — a fundamentally different compute profile on commodity CPUs. If 5-7 tok/s on a single CPU for 100B-class models is reproducible, that's a real milestone for on-device inference. Framework is ready. Now we need someone to actually train the model.

Re: BitNet: Inference framework for 1-bit LLMs

#7
> bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU and GPU (NPU support will coming next).

One bit or one trit? I am confused!

Re: BitNet: Inference framework for 1-bit LLMs

#8
post #7

> bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU and GPU (NPU support will coming next). One bit or one trit? I am confused!

"1-bit LLMs" is just marketing. The Shannon entropy of one letter with a 3 symbol alphabet (-1, 0, 1) is 1.58.

Re: BitNet: Inference framework for 1-bit LLMs

#10

headline hundred billion parameter, none of the official models are over 10 billion parameters. Curious.

The project is an inference framework which should support 100B parameter model at 5-7tok/s on CPU. No one has quantized a 100B parameter model to 1 trit, but this existing is an incentive for someone to do so.
Post reply on HN