LU

Luxia 21.4B 16bit

LuxiaGGUF by crimsonjooUpdated 2024-03-18
Download on Hugging Face
Parameters21.4B
Context32K
Layers52
Architecturellama
Smallest quant42.8 GB
Quick answer

Luxia 21.4B 16bit needs about 45.1 GB of memory at F16 (a 42.8 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 7.0 GB.

Luxia 21.4B 16bit is a 21.4B-parameter Luxia model in GGUF format, quantized by crimsonjoo. Its trained context length is 32K tokens. The repository has 1 quant file, from 42.8 GB (F16) to 42.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1642.8 GB 45.1 GB
Too big Get file →

What GPU do you need for Luxia 21.4B 16bit?

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 F16 (42.8 GB file, about 45.1 GB in use).

Which Luxia 21.4B 16bit quant should you choose?

F16 (42.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters21.4B
Layers52
Trained context32,768 tokens
KV cache (fp16)208 KB per token

Source

Quantized bycrimsonjoo
FamilyLuxia
Licenseapache-2.0
Downloads (HF)18
Last updated2024-03-18

Frequently asked questions about Luxia 21.4B 16bit

How much VRAM does Luxia 21.4B 16bit need?

About 45.1 GB at F16 with an 8K context window. That is the 42.8 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 Luxia 21.4B 16bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 45.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Luxia 21.4B 16bit GGUF?

It depends on the quant: F16 is 42.8 GB.

What context length does Luxia 21.4B 16bit support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 7.0 GB at 32K.

Where can I download Luxia 21.4B 16bit GGUF?

The files are on Hugging Face in the crimsonjoo/Luxia-21.4B-16bit-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 Luxia 21.4B 16bit 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 luxia-21.4b-alignment-v1.2

Similar models

Browse all →

More from crimsonjoo

All by crimsonjoo →

More Luxia models

All Luxia →

Other medium models

All medium models →