Model Anatomy See what's inside open-weight AI models

Can I run AliceAI-Foundation-80B-A3B-Base on an NVIDIA H100?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 45.7 GB) would fit, with room for ≈ 256K tokens of context. The site hasn't analyzed a GGUF of AliceAI-Foundation-80B-A3B-Base yet.

Full analysis of AliceAI-Foundation-80B-A3B-Base Everything that runs on NVIDIA H100

Files and context on NVIDIA H100

Each file of AliceAI-Foundation-80B-A3B-Base (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn NVIDIA H100 Context (16-bit)Context (8-bit)
As published163 GBDoesn't fit——
4-bit (estimate)45.7 GBFits256K256K

AliceAI-Foundation-80B-A3B-Base on other hardware

Popular models that run on NVIDIA H100

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.