DU

Dusk_Rainbow

DuskGGUF by dasChronos1Updated 2024-09-05
Download on Hugging Face
Parameters10.6B
Context10K
Layers44
Architecturellama
Smallest quant11.3 GB
Quick answer

Dusk_Rainbow needs about 13.3 GB of memory at Q8_0 (a 11.3 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Dusk_Rainbow is a 10.6B-parameter Dusk model in GGUF format, quantized by dasChronos1. Its trained context length is 10K tokens. The repository has 1 quant file, from 11.3 GB (Q8_0) to 11.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_011.3 GB 13.3 GB
Too big Get file →

What GPU do you need for Dusk_Rainbow?

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 Q8_0 (11.3 GB file, about 13.3 GB in use).

Which Dusk_Rainbow quant should you choose?

Q8_0 (11.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.6B
Layers44
Trained context10,240 tokens
KV cache (fp16)176 KB per token

Source

Quantized bydasChronos1
FamilyDusk
Downloads (HF)14
Last updated2024-09-05

Frequently asked questions about Dusk_Rainbow

How much VRAM does Dusk_Rainbow need?

About 13.3 GB at Q8_0 with an 8K context window. That is the 11.3 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 Dusk_Rainbow on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dusk_Rainbow GGUF?

It depends on the quant: Q8_0 is 11.3 GB.

What context length does Dusk_Rainbow support?

The GGUF header lists a trained context length of 10,240 tokens (10K). The KV cache grows with the context you use: about 1.5 GB at 8K and 1.8 GB at 10K.

Where can I download Dusk_Rainbow GGUF?

The files are on Hugging Face in the dasChronos1/DuskRainbowXL-10.6B-Q8_0-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 dasChronos1

All by dasChronos1 →

More Dusk models

All Dusk →

Other medium models

All medium models →