ST

Step 3.7 Flash AEON Ultimate Abliterated

StepGGUF by VegssUpdated 2026-06-08
Download on Hugging Face
Parameters197B
Context256K
Layers45
Architecturestep35
Smallest quant48.4 GB
Quick answer

Step 3.7 Flash AEON Ultimate Abliterated needs about 114.1 GB of memory at Q3_K_M (a 101.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 48.4 GB (IQ1_M) to 209.4 GB (Q8_0).

Step 3.7 Flash AEON Ultimate Abliterated – a 198B sparse‑MoE vision‑language model

Step 3.7 Flash AEON Ultimate Abliterated is a 198B‑parameter, 262144‑token context vision‑language model. It is a sparse‑MoE with reasoning, tools, and vision abilities. The model is released under Apache‑2.0 and is intended for authorized safety research and uncensored local deployment.

Good at

  • Reasoning and chain‑of‑thought
  • Tool use
  • Vision‑language tasks

Limits

  • Experimental GGUFs produce garbled output until llama.cpp bug fixed
  • Requires BF16 for coherent output
  • Large VRAM and RAM needed

Best for

  • Safety research and red‑team testing
  • Uncensored local deployment
  • Vision‑language inference

Who it’s for. Researchers and developers who need a large sparse‑MoE vision‑language model for safety testing or local deployment. The model is unaligned and requires downstream safety layers.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M48.4 GB (2 parts) 54.7 GB
Too big Get file →
Q3_K_M101.4 GB (3 parts) 114.1 GB
Too big Get file →
Q8_0209.4 GB (5 parts) 235.0 GB
Too big Get file →

For 8 k context, IQ1_M needs about 54.7 GB VRAM and 48.39 GB file size. Q3_K_M requires about 114.1 GB VRAM and 101.41 GB file size. Q8_0 needs about 235 GB VRAM and 209.42 GB file size. Choose the quant that fits your memory budget.

What GPU do you need for Step 3.7 Flash AEON Ultimate Abliterated?

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 3.7 Flash AEON Ultimate Abliterated quant should you choose?

Q3_K_M (101.4 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 IQ1_M at 48.4 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 byVegss
FamilyStep
Licenseapache-2.0
Downloads (HF)2,263
Last updated2026-06-08

Frequently asked questions about Step 3.7 Flash AEON Ultimate Abliterated

How much VRAM does Step 3.7 Flash AEON Ultimate Abliterated need?

About 114.1 GB at Q3_K_M with an 8K context window. That is the 101.4 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 3.7 Flash AEON Ultimate Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Step 3.7 Flash AEON Ultimate Abliterated GGUF?

It depends on the quant: IQ1_M is 48.4 GB, Q3_K_M is 101.4 GB, Q8_0 is 209.4 GB.

What context length does Step 3.7 Flash AEON Ultimate Abliterated support?

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

Where can I download Step 3.7 Flash AEON Ultimate Abliterated GGUF?

The files are on Hugging Face in the Vegss/Step-3.7-Flash-AEON-Ultimate-Abliterated-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 3.7 Flash AEON Ultimate Abliterated 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.

Can I run this model on 8 GB VRAM?

No. The smallest quant requires 54.7 GB VRAM at 8 k context.

Is the model safe to use out of the box?

The model is unaligned and experimental; it requires downstream safety layers and a corrected llama.cpp implementation.

What license applies to this model?

Apache‑2.0, inherited from the parent model.

Similar models

Browse all →

More from Vegss

All by Vegss →

More Step models

All Step →

Other large models

All large models →