Can I run Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata on an NVIDIA B300?

Yes

Its ple-fp8 file (51.2 GB) fits in the 259 GB an NVIDIA B300 can use, with room for an unknown amount of context.

Full analysis of Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata Everything that runs on NVIDIA B300 Get the ple-fp8 file on Hugging Face

ollama run hf.co/Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata

Files and context on NVIDIA B300

Each file of Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata (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)
ple-fp8	51.2 GB	Fits	not known	not known
qwen-nvfp4-gptq-dense	5.99 GB	Fits	not known	not known
BF16	1.27 GB	Fits	not known	not known

Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata 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.