CE

Celeste 12B V1.6 Q2 K

CelesteGGUF by Lucy-in-the-SkyUpdated 2024-12-20
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

Celeste 12B V1.6 Q2 K needs about 6.6 GB of memory at Q2_K (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Celeste 12B V1.6 Q2 K is a 12.2B-parameter Celeste model in GGUF format, quantized by Lucy-in-the-Sky. Its trained context length is 1000K tokens. The repository has 1 quant file, from 4.8 GB (Q2_K) to 4.8 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →

What GPU do you need for Celeste 12B V1.6 Q2 K?

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: the best quant that fits is Q2_K (4.8 GB file, about 6.6 GB in use).

Which Celeste 12B V1.6 Q2 K quant should you choose?

Q2_K (4.8 GB) is the middle option in this repository. 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

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byLucy-in-the-Sky
FamilyCeleste
Licenseapache-2.0
Downloads (HF)19
Last updated2024-12-20

Frequently asked questions about Celeste 12B V1.6 Q2 K

How much VRAM does Celeste 12B V1.6 Q2 K need?

About 6.6 GB at Q2_K with an 8K context window. That is the 4.8 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 Celeste 12B V1.6 Q2 K on an 8 GB GPU?

Yes, with Q2_K: the 4.8 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Celeste 12B V1.6 Q2 K GGUF?

It depends on the quant: Q2_K is 4.8 GB.

What context length does Celeste 12B V1.6 Q2 K support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Celeste 12B V1.6 Q2 K GGUF?

The files are on Hugging Face in the Lucy-in-the-Sky/Celeste-12B-V1.6-Q2_K-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 Celeste 12B V1.6 Q2 K 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 Celeste-12B-V1.6

Similar models

Browse all →

More from Lucy-in-the-Sky

All by Lucy-in-the-Sky →

More Celeste models

All Celeste →

Other medium models

All medium models →