DA

Luna dream 02

DaringmaidGGUF by JebadiahUpdated 2025-01-06
Download on Hugging Face
Parameters20B
Context250K
Layers62
Architecturellama
Smallest quant21.2 GB
Quick answer

Luna dream 02 needs about 32.1 GB of memory at Q8_0 (a 21.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 41.6 GB.

Luna dream 02 is a 20B-parameter Daringmaid model in GGUF format, quantized by Jebadiah. Its trained context length is 250K tokens. The repository has 1 quant file, from 21.2 GB (Q8_0) to 21.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_021.2 GB 32.1 GB
Too big Get file →

What GPU do you need for Luna dream 02?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q8_0 (21.2 GB file, about 32.1 GB in use).

Which Luna dream 02 quant should you choose?

Q8_0 (21.2 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
Parameters20B
Layers62
Trained context256,000 tokens
KV cache (fp16)1240 KB per token

Source

Quantized byJebadiah
Licenseapache-2.0
Downloads (HF)34
Last updated2025-01-06

Frequently asked questions about Luna dream 02

How much VRAM does Luna dream 02 need?

About 32.1 GB at Q8_0 with an 8K context window. That is the 21.2 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 Luna dream 02 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Luna dream 02 GGUF?

It depends on the quant: Q8_0 is 21.2 GB.

What context length does Luna dream 02 support?

The GGUF header lists a trained context length of 256,000 tokens (250K). The KV cache grows with the context you use: about 10.4 GB at 8K and 41.6 GB at 32K.

Where can I download Luna dream 02 GGUF?

The files are on Hugging Face in the Jebadiah/Luna-dream-02 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Luna dream 02 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.

Other GGUFs of DaringMaid-20B

Similar models

Browse all →

More from Jebadiah

All by Jebadiah →

More Daringmaid models

All Daringmaid →

Other medium models

All medium models →