OR

Orion 14B Chat

OrionGGUF by condblockUpdated 2024-11-28
Download on Hugging Face
Parameters14.5B
Context4K
Layers40
Architectureorion
Smallest quant10.3 GB
Quick answer

Orion 14B Chat needs about 17.5 GB of memory at Q5_K_M (a 10.3 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Orion 14B Chat is a 14.5B-parameter Orion model in GGUF format, quantized by condblock. Its trained context length is 4K tokens. The repository has 1 quant file, from 10.3 GB (Q5_K_M) to 10.3 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.3 GB 14.2 GB
Too big Get file →

What GPU do you need for Orion 14B Chat?

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 Q5_K_M (10.3 GB file, about 17.5 GB in use).

Which Orion 14B Chat quant should you choose?

Q5_K_M (10.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 bycondblock
FamilyOrion
Downloads (HF)4
Last updated2024-11-28

Frequently asked questions about Orion 14B Chat

How much VRAM does Orion 14B Chat need?

About 17.5 GB at Q5_K_M with an 8K context window. That is the 10.3 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 Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Orion 14B Chat GGUF?

It depends on the quant: Q5_K_M is 10.3 GB.

What context length does Orion 14B Chat 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 Chat GGUF?

The files are on Hugging Face in the condblock/Orion-14B-Chat-Q5_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Orion-14B-Chat

Similar models

Browse all →

More Orion models

All Orion →

Other medium models

All medium models →