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

Can I run NeoHorse-1-4B on an NVIDIA H100?

Yes

Its published weights (8.41 GB) fit in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 256K tokens of context.

Full analysis of NeoHorse-1-4B Everything that runs on NVIDIA H100 Get the weights on Hugging Face
hf download TokenRhythm/NeoHorse-1-4B

Files and context on NVIDIA H100

Each file of NeoHorse-1-4B (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 published8.41 GBFits256K256K
BF16TokenRhythm/NeoHorse-1-4B-GGUF8.42 GBFits256K256K
F16TokenRhythm/NeoHorse-1-4B-GGUF8.42 GBFits256K256K
Q8_0TokenRhythm/NeoHorse-1-4B-GGUF4.48 GBFits256K256K
Q5_K_MTokenRhythm/NeoHorse-1-4B-GGUF3.07 GBFits256K256K
Q4_K_MTokenRhythm/NeoHorse-1-4B-GGUF2.71 GBFits256K256K

NeoHorse-1-4B 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.