OR

Ornith 1.0 397B APEX

OrnithGGUF by Merlinoz11Updated 2026-06-28
Download on Hugging Face
Parameters396B
Context256K
Layers60
Architectureqwen35moe
Smallest quant163.1 GB
Quick answer

Ornith 1.0 397B APEX needs about 164.6 GB of memory at its main file (a 163.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 163.1 GB to 204.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.

Ornith 1.0 397B APEX is a 396B-parameter Ornith model in GGUF format, quantized by Merlinoz11. Its trained context length is 256K tokens. The repository has 2 quant files, from 163.1 GB to 204.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—163.1 GB 164.6 GB
Too big Get file →
—204.9 GB 206.4 GB
Too big Get file →

What GPU do you need for Ornith 1.0 397B APEX?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters396B (approximate, mixture of experts)
Layers60
Trained context262,144 tokens
KV cache (fp16)120 KB per token

Source

Quantized byMerlinoz11
FamilyOrnith
Licensemit
Downloads (HF)144
Last updated2026-06-28

Frequently asked questions about Ornith 1.0 397B APEX

How much VRAM does Ornith 1.0 397B APEX need?

About 164.6 GB at its main file with an 8K context window. That is the 163.1 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 Ornith 1.0 397B APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 164.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornith 1.0 397B APEX GGUF?

It depends on the quant: file is 163.1 GB, file is 204.9 GB.

What context length does Ornith 1.0 397B APEX support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.

Where can I download Ornith 1.0 397B APEX GGUF?

The files are on Hugging Face in the Merlinoz11/Ornith-1.0-397B-APEX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ornith 1.0 397B APEX use?

Hugging Face lists the license as mit. 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 Ornith-1.0-397B

Similar models

Browse all →

More from Merlinoz11

All by Merlinoz11 →

More Ornith models

All Ornith →

Other large models

All large models →