OR

Orbita-v0.1

OrbitaGGUF by NikolayKozloffUpdated 2024-04-25
Download on Hugging Face
Parameters14.2B
Context32K
Layers40
Architectureqwen2
Smallest quant10.5 GB
Quick answer

Orbita-v0.1 needs about 17.7 GB of memory at Q5_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

Orbita-v0.1 is a 14.2B-parameter Orbita model in GGUF format, quantized by NikolayKozloff. Its trained context length is 32K tokens. The repository has 1 quant file, from 10.5 GB (Q5_K_M) to 10.5 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.5 GB 17.7 GB
Too big Get file →

What GPU do you need for Orbita-v0.1?

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 (10.5 GB file, about 17.7 GB in use).

Which Orbita-v0.1 quant should you choose?

Q5_K_M (10.5 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

Architectureqwen2
Parameters14.2B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byNikolayKozloff
FamilyOrbita
Licenseapache-2.0
Downloads (HF)16
Last updated2024-04-25

Frequently asked questions about Orbita-v0.1

How much VRAM does Orbita-v0.1 need?

About 17.7 GB at Q5_K_M with an 8K context window. That is the 10.5 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 Orbita-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Orbita-v0.1 GGUF?

It depends on the quant: Q5_K_M is 10.5 GB.

What context length does Orbita-v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download Orbita-v0.1 GGUF?

The files are on Hugging Face in the NikolayKozloff/Orbita-v0.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Orbita-v0.1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Orbita models

All Orbita →

Other medium models

All medium models →