RU

rubra 9.5b basic v10

RubraGGUF by yingbeiUpdated 2024-04-23
Download on Hugging Face
Parameters9.42B
Context32K
Layers42
Architecturellama
Smallest quant10.0 GB
Quick answer

rubra 9.5b basic v10 needs about 11.9 GB of memory at its main file (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

rubra 9.5b basic v10 is a 9.42B-parameter Rubra model in GGUF format, quantized by yingbei. Its trained context length is 32K tokens. The repository has 1 quant file, from 10.0 GB to 10.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—10.0 GB 11.9 GB
Too big Get file →

What GPU do you need for rubra 9.5b basic v10?

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: the best quant that fits is the main file (10.0 GB file, about 11.9 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters9.42B
Layers42
Trained context32,768 tokens
KV cache (fp16)168 KB per token

Source

Quantized byyingbei
FamilyRubra
Downloads (HF)10
Last updated2024-04-23

Frequently asked questions about rubra 9.5b basic v10

How much VRAM does rubra 9.5b basic v10 need?

About 11.9 GB at its main file with an 8K context window. That is the 10.0 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 rubra 9.5b basic v10 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of rubra 9.5b basic v10 GGUF?

It depends on the quant: file is 10.0 GB.

What context length does rubra 9.5b basic v10 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download rubra 9.5b basic v10 GGUF?

The files are on Hugging Face in the yingbei/rubra-9.5b-basic-v10.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 yingbei

All by yingbei →

More Rubra models

All Rubra →

Other small models

All small models →