Step-3.7-Flash-NVFP4: hardware requirements

Step-3.7-Flash-NVFP4 needs about 148 GB of memory at Q4 quantization — a 129 GB download plus room for context and overhead. That is beyond consumer hardware; use it through an API instead.

Parameters
104B
Tier
Server only
Licence
See model card
Released
2026-06-01

Will it run on your machine?

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

QuantDownloadRAM @ 4KRAM @ 32KSource
Published129 GB148 GB148 GBmeasured

“Measured” sizes are read from published GGUF files (stepfun-ai/Step-3.7-Flash-NVFP4). “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.

Other sizes of Step-3.7-Flash

Model card on HuggingFace →API specs & pricing →Verified 2026-09-13Tracked for 12 months after release