ST

Step 5 Preview

StepGGUF by smalininUpdated 2026-10-24
Download on Hugging Face
Parameters601B
Context1024K
Layers—
Architecturestep35
Smallest quant1.2 GB
Quick answer

Step 5 Preview needs about 1.9 GB of memory at its main file (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.2 GB to 271.6 GB (IQ3_M).

Step 5 Preview – 600B total parameters, 27B active, up to 1M context

Step 5 Preview is StepFun's flagship sparse Mixture-of-Experts model. It contains 600B total parameters and 27B active parameters per token. The model supports up to 1M context and multimodal inputs such as text, images, and video.

Good at

  • Software engineering tasks
  • Long-horizon agentic execution
  • Professional knowledge work

Limits

  • No vision support in this GGUF release
  • Requires CUDA GPU for full inference
  • Large memory footprint for higher precision quants

Best for

  • Complex coding projects
  • Agentic workflows with tool use
  • Financial analysis with quantitative reasoning

Who it’s for. Developers and researchers needing advanced agentic and coding capabilities. The model is suitable for teams that can allocate sufficient GPU memory and have access to a CUDA-compatible environment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.2 GB 1.9 GB
Fits Get file →
—1.2 GB 1.9 GB
Fits Get file →
IQ2_XXS182.5 GB (8 parts) 204.9 GB
Too big Get file →
IQ3_M271.6 GB (8 parts) 304.7 GB
Too big Get file →

For 8 GB VRAM, use the IQ2_XXS quant (file size 182.47 GB, estimated memory 204.9 GB at 8 k context). For 16 GB VRAM, the IQ3_M quant (file size 271.61 GB, estimated memory 304.7 GB at 8 k context) is recommended. The unknown quant files are 1.22 GB each but memory estimates are not provided.

What GPU do you need for Step 5 Preview?

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: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.9 GB in use).

Which Step 5 Preview quant should you choose?

If memory is tight, the smallest file is the first one in the table at 1.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestep35
Parameters601B
Trained context1,048,576 tokens

Source

Quantized bysmalinin
FamilyStep
Licenseother
Downloads (HF)2,083
Last updated2026-10-24

Frequently asked questions about Step 5 Preview

How much VRAM does Step 5 Preview need?

About 1.9 GB at its main file with an 8K context window. That is the 1.2 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 5 Preview on an 8 GB GPU?

Yes, with the smaller files: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Step 5 Preview GGUF?

It depends on the quant: file is 1.2 GB, file is 1.2 GB, IQ2_XXS is 182.5 GB, IQ3_M is 271.6 GB.

What context length does Step 5 Preview support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Step 5 Preview GGUF?

The files are on Hugging Face in the smalinin/Step-5-Preview-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 5 Preview use?

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

Can I run Step 5 Preview on 8 GB VRAM?

The IQ2_XXS quant requires approximately 204.9 GB of memory at 8 k context, so 8 GB VRAM is insufficient.

Does Step 5 Preview support image input?

The model advertises multimodal support, but the GGUF release does not include vision support.

What is the context length of Step 5 Preview?

The model supports up to 1 M tokens of context.

Similar models

Browse all →

More from smalinin

All by smalinin →

More Step models

All Step →

Other large models

All large models →