ST

Stepfun ai.Step 3.5 Flash Base

StepGGUF by DevQuasarUpdated 2026-03-05
Download on Hugging Face
Parameters197B
Context32K
Layers45
Architecturestep35
Smallest quant71.8 GB
Quick answer

Stepfun ai.Step 3.5 Flash Base needs about 133.3 GB of memory at Q4_K_M (a 118.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 71.8 GB (Q2_K) to 139.5 GB (Q5_K_M).

Stepfun ai.Step 3.5 Flash Base is a 197B-parameter Step model in GGUF format, quantized by DevQuasar. Its trained context length is 32K tokens. The repository has 4 quant files, from 71.8 GB (Q2_K) to 139.5 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K71.8 GB (5 parts) 80.9 GB
Too big Get file →
MXFP4_MOE108.3 GB (7 parts) 121.8 GB
Too big Get file →
Q4_K_M118.6 GB (8 parts) 133.3 GB
Too big Get file →
Q5_K_M139.5 GB (10 parts) 156.7 GB
Too big Get file →

What GPU do you need for Stepfun ai.Step 3.5 Flash Base?

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 Stepfun ai.Step 3.5 Flash Base quant should you choose?

Q4_K_M is the usual starting point for Stepfun ai.Step 3.5 Flash Base: it balances file size and quality well. Here it is a 118.6 GB file.

If memory is tight, the smallest file is Q2_K at 71.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestep35
Parameters197B (approximate, mixture of experts)
Layers45
Trained context32,768 tokens

Source

Quantized byDevQuasar
FamilyStep
Licenseapache-2.0
Downloads (HF)103
Last updated2026-03-05

Frequently asked questions about Stepfun ai.Step 3.5 Flash Base

How much VRAM does Stepfun ai.Step 3.5 Flash Base need?

About 133.3 GB at Q4_K_M with an 8K context window. That is the 118.6 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 Stepfun ai.Step 3.5 Flash Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 80.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Stepfun ai.Step 3.5 Flash Base GGUF?

It depends on the quant: Q2_K is 71.8 GB, MXFP4_MOE is 108.3 GB, Q4_K_M is 118.6 GB, Q5_K_M is 139.5 GB.

What context length does Stepfun ai.Step 3.5 Flash Base support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download Stepfun ai.Step 3.5 Flash Base GGUF?

The files are on Hugging Face in the DevQuasar/stepfun-ai.Step-3.5-Flash-Base-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 Stepfun ai.Step 3.5 Flash Base 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-Base

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Step models

All Step →

Other large models

All large models →