ST

Step 3.5 Flash PRISM

StepGGUF by Ex0bitUpdated 2026-02-12
Download on Hugging Face
Parameters197B
Context256K
Layers45
Architecturestep35
Smallest quant64.0 GB
Quick answer

Step 3.5 Flash PRISM needs about 114.8 GB of memory at Q3_K_L (a 102.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 64.0 GB (IQ2_M) to 111.5 GB (IQ4_NL).

Step 3.5 Flash PRISM – a 196B MoE model with 256K context

Step 3.5 Flash PRISM is a 196B parameter Mixture of Experts model with 11B active per token. It supports a 262144 token context window and is optimized for reasoning and tool use. The model is available in three GGUF quantizations.

Good at

  • Deep reasoning
  • Tool integration
  • Long‑context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is other

Best for

  • Agentic workflows
  • Complex coding tasks
  • Long‑form reasoning

Who it’s for. Developers and researchers needing a high‑capacity, long‑context LLM for agentic or coding applications. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M64.0 GB 72.2 GB
Too big Get file →
Q3_K_L102.0 GB 114.8 GB
Too big Get file →
IQ4_NL111.5 GB 125.4 GB
Too big Get file →

For 8 GB VRAM, use IQ2_M (63.98 GB file, 72.2 GB memory at 8K context). For 12 GB VRAM, Q3_K_L (102.04 GB file, 114.8 GB memory). For 16 GB VRAM, IQ4_NL (111.52 GB file, 125.4 GB memory). Estimates are approximate.

What GPU do you need for Step 3.5 Flash PRISM?

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 PRISM quant should you choose?

Q3_K_L (102.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_M at 64.0 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 context262,144 tokens

Source

Quantized byEx0bit
FamilyStep
Licenseother
Downloads (HF)490
Last updated2026-02-12

Frequently asked questions about Step 3.5 Flash PRISM

How much VRAM does Step 3.5 Flash PRISM need?

About 114.8 GB at Q3_K_L with an 8K context window. That is the 102.0 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 PRISM on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 72.2 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ2_M is 64.0 GB, Q3_K_L is 102.0 GB, IQ4_NL is 111.5 GB.

What context length does Step 3.5 Flash PRISM support?

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

Where can I download Step 3.5 Flash PRISM GGUF?

The files are on Hugging Face in the Ex0bit/Step-3.5-Flash-PRISM 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 PRISM 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 PRISM on 8 GB VRAM?

The IQ2_M quantization requires about 72.2 GB memory at 8K context, so 8 GB VRAM is insufficient.

Does the model support vision?

No, the model has no vision capabilities.

What context length does it support?

It supports a 262144 token context window.

Other GGUFs of Step-3.5-Flash

Similar models

Browse all →

More from Ex0bit

All by Ex0bit →

More Step models

All Step →

Other large models

All large models →