Ornith 1.0 397B Featherweight needs about 121.0 GB of memory at its main file (a 119.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
Ornith 1.0 397B Featherweight is a 396B-parameter Ornith model in GGUF format, quantized by SEBK4C. Its trained context length is 256K tokens. The repository has 1 quant file, from 119.5 GB to 119.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 119.5 GB | 121.0 GB | Too big | Get file → |
What GPU do you need for Ornith 1.0 397B Featherweight?
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
Source
Frequently asked questions about Ornith 1.0 397B Featherweight
How much VRAM does Ornith 1.0 397B Featherweight need?
About 121.0 GB at its main file with an 8K context window. That is the 119.5 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 Featherweight on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 121.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.0 397B Featherweight GGUF?
It depends on the quant: file is 119.5 GB.
What context length does Ornith 1.0 397B Featherweight 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 Featherweight GGUF?
The files are on Hugging Face in the SEBK4C/Ornith-1.0-397B-Featherweight 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 Featherweight 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.