ST

Step 3.5 Flash MXFP4 MOE

StepGGUF by noctrexUpdated 2026-02-10
Download on Hugging Face
Parameters197B
Context256K
Layers45
Architecturestep35
Smallest quant108.3 GB
Quick answer

Step 3.5 Flash MXFP4 MOE needs about 121.8 GB of memory at MXFP4_MOE (a 108.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

Step 3.5 Flash MXFP4 MOE is a 197B-parameter Step model in GGUF format, quantized by noctrex. Its trained context length is 256K tokens. The repository has 1 quant file, from 108.3 GB (MXFP4_MOE) to 108.3 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE108.3 GB (7 parts) 121.8 GB
Too big Get file →

What GPU do you need for Step 3.5 Flash MXFP4 MOE?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Step 3.5 Flash MXFP4 MOE quant should you choose?

MXFP4_MOE (108.3 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestep35
Parameters197B (approximate, mixture of experts)
Layers45
Trained context262,144 tokens

Source

Quantized bynoctrex
FamilyStep
Licenseapache-2.0
Downloads (HF)20
Last updated2026-02-10

Frequently asked questions about Step 3.5 Flash MXFP4 MOE

How much VRAM does Step 3.5 Flash MXFP4 MOE need?

About 121.8 GB at MXFP4_MOE with an 8K context window. That is the 108.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Step 3.5 Flash MXFP4 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 121.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Step 3.5 Flash MXFP4 MOE GGUF?

It depends on the quant: MXFP4_MOE is 108.3 GB.

What context length does Step 3.5 Flash MXFP4 MOE support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Step 3.5 Flash MXFP4 MOE GGUF?

The files are on Hugging Face in the noctrex/Step-3.5-Flash-MXFP4_MOE-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Step 3.5 Flash MXFP4 MOE use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Step-3.5-Flash

Similar models

Browse all →

More from noctrex

All by noctrex →

More Step models

All Step →

Other large models

All large models →