Ornith 1.5 397B GGUF imatrix needs about 157.5 GB of memory at IQ2_M (a 140.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 1.1 GB to 251.0 GB (Q4_K_XL).
Ornith 1.5 397B GGUF imatrix is a 403B-parameter Ornith model in GGUF format, quantized by cdanis. Its trained context length is 256K tokens. The repository has 11 quant files, from 1.1 GB to 251.0 GB (Q4_K_XL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.1 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 92.2 GB | 103.8 GB | Too big | Get file → | |
| IQ1_M | 100.9 GB | 113.6 GB | Too big | Get file → | |
| IQ2_XXS | 115.5 GB | 129.8 GB | Too big | Get file → | |
| IQ2_S | 128.6 GB | 144.5 GB | Too big | Get file → | |
| IQ2_M | 140.2 GB | 157.5 GB | Too big | Get file → | |
| IQ3_XXS | 162.7 GB | 182.7 GB | Too big | Get file → | |
| IQ3_S | 181.0 GB | 203.2 GB | Too big | Get file → | |
| Q3_K_XL | 187.2 GB | 210.1 GB | Too big | Get file → | |
| IQ4_XS | 224.8 GB | 252.2 GB | Too big | Get file → | |
| Q4_K_XL | 251.0 GB | 281.7 GB | Too big | Get file → |
What GPU do you need for Ornith 1.5 397B GGUF imatrix?
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: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
Which Ornith 1.5 397B GGUF imatrix quant should you choose?
IQ2_M (140.2 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is the first one in the table at 1.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 397B GGUF imatrix
How much VRAM does Ornith 1.5 397B GGUF imatrix need?
About 157.5 GB at IQ2_M with an 8K context window. That is the 140.2 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 1.5 397B GGUF imatrix on an 8 GB GPU?
Yes, with the smaller files: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ornith 1.5 397B GGUF imatrix GGUF?
It depends on the quant: file is 1.1 GB, IQ1_S is 92.2 GB, IQ1_M is 100.9 GB, IQ2_XXS is 115.5 GB, IQ2_S is 128.6 GB, IQ2_M is 140.2 GB and 5 more.
What context length does Ornith 1.5 397B GGUF imatrix support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Ornith 1.5 397B GGUF imatrix GGUF?
The files are on Hugging Face in the cdanis/Ornith-1.5-397B-GGUF-imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.