OR

Orion 14B Base

OrionGGUF by mradermacherUpdated 2024-12-06
Download on Hugging Face
Parameters14.5B
Context4K
Layers40
Architectureorion
Smallest quant5.5 GB
Quick answer

Orion 14B Base needs about 16.0 GB of memory at Q4_K_M (a 8.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.5 GB (Q2_K) to 15.4 GB (Q8_0).

Orion 14B Base is a 14.5B-parameter Orion model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 12 quant files, from 5.5 GB (Q2_K) to 15.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.5 GB 9.4 GB
Too big Get file →
Q3_K_S6.4 GB 10.3 GB
Too big Get file →
Q3_K_M7.1 GB 11.0 GB
Too big Get file →
Q3_K_L7.8 GB 11.6 GB
Too big Get file →
IQ4_XS7.9 GB 11.7 GB
Too big Get file →
Q4_08.3 GB 12.1 GB
Too big Get file →
Q4_K_S8.3 GB 12.2 GB
Too big Get file →
Q4_K_M8.8 GB 12.7 GB
Too big Get file →
Q5_K_S10.0 GB 13.9 GB
Too big Get file →
Q5_K_M10.3 GB 14.2 GB
Too big Get file →
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: the best quant that fits is Q4_K_M (8.8 GB file, about 16.0 GB in use).
  • 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?

Q4_K_M is the usual starting point for Orion 14B Base: it balances file size and quality well. Here it is a 8.8 GB file.

The Q8_0 file is 15.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.5 GB, with the quality trade-offs that come with fewer bits. 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.

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 bymradermacher
FamilyOrion
Downloads (HF)307
Last updated2024-12-06

Frequently asked questions about Orion 14B Base

How much VRAM does Orion 14B Base need?

About 16.0 GB at Q4_K_M with an 8K context window. That is the 8.8 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 12.7 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: Q2_K is 5.5 GB, Q3_K_S is 6.4 GB, Q3_K_M is 7.1 GB, Q3_K_L is 7.8 GB, IQ4_XS is 7.9 GB, Q4_0 is 8.3 GB and 6 more.

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 mradermacher/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.

Other GGUFs of Orion-14B-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Orion models

All Orion →

Other medium models

All medium models →