OR

Orion-14B-Base

OrionGGUF by demonsuUpdated 2024-01-25
Download on Hugging Face
Parameters14.5B
Context4K
Layers40
Architectureorion
Smallest quant11.9 GB
Quick answer

Orion-14B-Base needs about 19.1 GB of memory at Q6_K (a 11.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 11.9 GB (Q6_K) to 15.4 GB (Q8_0).

Orion-14B-Base is a 14.5B-parameter Orion model in GGUF format, quantized by demonsu. Its trained context length is 4K tokens. The repository has 2 quant files, from 11.9 GB (Q6_K) to 15.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K11.9 GB 15.8 GB
Too big Get file →
Q8_015.4 GB 19.3 GB
Too big Get file →

What GPU do you need for Orion-14B-Base?

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: the best quant that fits is Q8_0 (15.4 GB file, about 22.6 GB in use).

Which Orion-14B-Base quant should you choose?

Q6_K (11.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureorion
Parameters14.5B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bydemonsu
FamilyOrion
Downloads (HF)10
Last updated2024-01-25

Frequently asked questions about Orion-14B-Base

How much VRAM does Orion-14B-Base need?

About 19.1 GB at Q6_K with an 8K context window. That is the 11.9 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 Orion-14B-Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Orion-14B-Base GGUF?

It depends on the quant: Q6_K is 11.9 GB, Q8_0 is 15.4 GB.

What context length does Orion-14B-Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Orion-14B-Base GGUF?

The files are on Hugging Face in the demonsu/orion-14b-base-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from demonsu

All by demonsu →

More Orion models

All Orion →

Other medium models

All medium models →