Can I run Ternary-Bonsai-27B-gguf on an NVIDIA H100?

Yes

Its F16 file (53.8 GB) fits in the 72.0 GB an NVIDIA H100 can use, with room for ≈ 4K tokens of context.

Full analysis of Ternary-Bonsai-27B-gguf Everything that runs on NVIDIA H100 Get the F16 file on Hugging Face

ollama run hf.co/prism-ml/Ternary-Bonsai-27B-gguf:F16

Files and context on NVIDIA H100

Each file of Ternary-Bonsai-27B-gguf (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.

File	Size	On NVIDIA H100	Context (16-bit)	Context (8-bit)
F16	53.8 GB	Fits	4K	4K
Ternary-Bonsai-27B-Q2_g64	7.59 GB	Fits	4K	4K
BF16	7.29 GB	Fits	4K	4K
Ternary-Bonsai-27B-PQ2_0	7.17 GB	Fits	4K	4K
Ternary-Bonsai-27B-Q2_0	7.17 GB	Fits	4K	4K
Q4_1	1.95 GB	Fits	4K	4K

Ternary-Bonsai-27B-gguf 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.