ST

Step 3.5 Flash APEX

StepGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters197B
Context256K
Layers45
Architecturestep35
Smallest quant76.5 GB
Quick answer

Step 3.5 Flash APEX needs about 138.4 GB of memory at its main file (a 123.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 76.5 GB to 143.1 GB.

Step 3.5 Flash APEX – a sparse Mixture of Experts model with 256K context

Step 3.5 Flash APEX is a 196B parameter model built on a sparse Mixture of Experts architecture. It activates only 11B parameters per token and supports a 256K token context window. The model is available in multiple GGUF quantizations with varying file sizes.

Good at

  • Deep reasoning and agentic tasks
  • Long‑context coding
  • Real‑time interaction

Limits

  • Requires high‑end GPU memory for full model
  • No vision support
  • License type is other

Best for

  • Developers building agentic applications
  • Researchers testing long‑context performance
  • Local deployment on powerful consumer hardware

Who it’s for. The model is suitable for developers and researchers who need a large‑scale, sparse MoE model for reasoning, coding, and agentic tasks. It is designed for local deployment on high‑end GPUs and requires significant VRAM to run efficiently.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—76.5 GB 86.2 GB
Too big Get file →
—93.0 GB 104.7 GB
Too big Get file →
—93.0 GB 104.7 GB
Too big Get file →
—123.1 GB 138.4 GB
Too big Get file →
—123.1 GB 138.4 GB
Too big Get file →
—143.1 GB 160.8 GB
Too big Get file →
—143.1 GB 160.8 GB
Too big Get file →

For 8 GB VRAM, use the 76.51 GB file (est. 86.2 GB memory at 8K context). For 16 GB VRAM, the 93 GB file (est. 104.7 GB memory) is the next option. For 32 GB VRAM, the 123.14 GB file (est. 138.4 GB memory) can be considered. Memory estimates are approximate.

What GPU do you need for Step 3.5 Flash APEX?

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 APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 76.5 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
Parameters197B (approximate, mixture of experts)
Layers45
Trained context262,144 tokens

Source

Quantized bymudler
FamilyStep
Licenseother
Downloads (HF)1,117
Last updated2026-08-17

Frequently asked questions about Step 3.5 Flash APEX

How much VRAM does Step 3.5 Flash APEX need?

About 138.4 GB at its main file with an 8K context window. That is the 123.1 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 APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 86.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Step 3.5 Flash APEX GGUF?

It depends on the quant: file is 76.5 GB, file is 93.0 GB, file is 93.0 GB, file is 123.1 GB, file is 123.1 GB, file is 143.1 GB and 1 more.

What context length does Step 3.5 Flash APEX support?

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

Where can I download Step 3.5 Flash APEX GGUF?

The files are on Hugging Face in the mudler/Step-3.5-Flash-APEX-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 APEX 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 3.5 Flash APEX on 8 GB VRAM?

The smallest quantized file is 76.51 GB, which requires approximately 86.2 GB of VRAM at 8K context. 8 GB VRAM is insufficient.

Does Step 3.5 Flash APEX support vision tasks?

No, the model does not include vision capabilities.

Other GGUFs of Step-3.5-Flash

Similar models

Browse all →

More from mudler

All by mudler →

More Step models

All Step →

Other large models

All large models →