Can I run Ripple-65B-Preview-GGUF on an NVIDIA B300?

Yes

Its BF16 file (130 GB) fits in the 259 GB an NVIDIA B300 can use, with room for ≈ 1.9M tokens of context.

Full analysis of Ripple-65B-Preview-GGUF Everything that runs on NVIDIA B300 Get the BF16 file on Hugging Face

llama-server -hf AtomicChat/Ripple-65B-Preview-GGUF:BF16

Files and context on NVIDIA B300

Each file of Ripple-65B-Preview-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 B300	Context (16-bit)	Context (8-bit)
BF16	130 GB	Fits	1.9M	2M
Q8_0	68.8 GB	Fits	2M	2M
Q6_K	57.7 GB	Fits	2M	2M
Q5_K_M	47.9 GB	Fits	2M	2M
Q4_K_M	40.4 GB	Fits	2M	2M
Ripple-65B-Preview-Q4_K_M	38.8 GB	Fits	2M	2M
IQ4_XS	38.7 GB	Fits	2M	2M
IQ3_S	32.4 GB	Fits	2M	2M
IQ3_XXS	28.0 GB	Fits	2M	2M
IQ2_S	25.3 GB	Fits	2M	2M
IQ2_XS	22.1 GB	Fits	2M	2M
IQ2_XXS	20.0 GB	Fits	2M	2M
IQ1_M	18.5 GB	Fits	2M	2M

Ripple-65B-Preview-GGUF on other hardware

Popular models that run on NVIDIA B300

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.