PR

Hy4 preview FlashMoE STQ1 0

PreviewGGUF by anemllUpdated 2026-09-03
Download on Hugging Face
Parameters25.8B
Context1024K
Layers78
Architecturehyv4
Smallest quant22.7 GB
Quick answer

Hy4 preview FlashMoE STQ1 0 needs about 24.5 GB of memory at its main file (a 22.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Hy4 preview FlashMoE STQ1 0 is a 25.8B-parameter Preview model in GGUF format, quantized by anemll. Its trained context length is 1024K tokens. The repository has 1 quant file, from 22.7 GB to 22.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—22.7 GB 24.5 GB
Too big Get file →

What GPU do you need for Hy4 preview FlashMoE STQ1 0?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is the main file (22.7 GB file, about 24.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturehyv4
Parameters25.8B (approximate, mixture of experts)
Layers78
Trained context1,048,576 tokens
KV cache (fp16)166 KB per token

Source

Quantized byanemll
FamilyPreview
Licenseapache-2.0
Downloads (HF)57
Last updated2026-09-03

Frequently asked questions about Hy4 preview FlashMoE STQ1 0

How much VRAM does Hy4 preview FlashMoE STQ1 0 need?

About 24.5 GB at its main file with an 8K context window. That is the 22.7 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 Hy4 preview FlashMoE STQ1 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Hy4 preview FlashMoE STQ1 0 GGUF?

It depends on the quant: file is 22.7 GB.

What context length does Hy4 preview FlashMoE STQ1 0 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Hy4 preview FlashMoE STQ1 0 GGUF?

The files are on Hugging Face in the anemll/Hy4-preview-FlashMoE-STQ1_0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Hy4 preview FlashMoE STQ1 0 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 Hy4-preview

Similar models

Browse all →

More from anemll

All by anemll →

More Preview models

All Preview →

Other medium models

All medium models →