LU

Luxia 21.4b Alignment v1.2

LuxiaGGUF by RichardErkhovUpdated 2024-10-29
Download on Hugging Face
Parameters21.4B
Context32K
Layers52
Architecturellama
Smallest quant8.1 GB
Quick answer

Luxia 21.4b Alignment v1.2 needs about 15.2 GB of memory at Q4_K_M (a 12.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 19 quants, from 8.1 GB (Q2_K) to 22.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.0 GB.

Luxia 21.4b Alignment v1.2 is a 21.4B-parameter Luxia model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 19 quant files, from 8.1 GB (Q2_K) to 22.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.1 GB 10.4 GB
Too big Get file →
Q3_K_S9.4 GB 11.7 GB
Too big Get file →
Q3_K10.5 GB 12.7 GB
Too big Get file →
Q3_K_M10.5 GB 12.7 GB
Too big Get file →
Q3_K_L11.4 GB 13.6 GB
Too big Get file →
IQ4_XS11.7 GB 13.9 GB
Too big Get file →
Q4_012.2 GB 14.4 GB
Too big Get file →
Q4_K_S12.3 GB 14.5 GB
Too big Get file →
IQ4_NL12.3 GB 14.6 GB
Too big Get file →
Q4_K12.9 GB 15.2 GB
Too big Get file →
Q4_K_M12.9 GB 15.2 GB
Too big Get file →
Q4_113.5 GB 15.7 GB
Too big Get file →
Q5_014.8 GB 17.1 GB
Too big Get file →
Q5_K_S14.8 GB 17.1 GB
Too big Get file →
Q5_K15.2 GB 17.4 GB
Too big Get file →
Q5_K_M15.2 GB 17.4 GB
Too big Get file →
Q5_116.1 GB 18.4 GB
Too big Get file →
Q6_K17.6 GB 19.8 GB
Too big Get file →
Q8_022.8 GB 25.0 GB
Too big Get file →

What GPU do you need for Luxia 21.4b Alignment v1.2?

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 Q3_K_S (9.4 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.6 GB file, about 19.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 25.0 GB in use).

Which Luxia 21.4b Alignment v1.2 quant should you choose?

Q4_K_M is the usual starting point for Luxia 21.4b Alignment v1.2: it balances file size and quality well. Here it is a 12.9 GB file.

The Q8_0 file is 22.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 8.1 GB, with the quality trade-offs that come with fewer bits. 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
Parameters21.4B
Layers52
Trained context32,768 tokens
KV cache (fp16)208 KB per token

Source

Quantized byRichardErkhov
FamilyLuxia
Licenseapache-2.0
Downloads (HF)73
Last updated2024-10-29

Frequently asked questions about Luxia 21.4b Alignment v1.2

How much VRAM does Luxia 21.4b Alignment v1.2 need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 12.9 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 Alignment v1.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Luxia 21.4b Alignment v1.2 GGUF?

It depends on the quant: Q2_K is 8.1 GB, Q3_K_S is 9.4 GB, Q3_K is 10.5 GB, Q3_K_M is 10.5 GB, Q3_K_L is 11.4 GB, IQ4_XS is 11.7 GB and 13 more.

What context length does Luxia 21.4b Alignment v1.2 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 Alignment v1.2 GGUF?

The files are on Hugging Face in the RichardErkhov/saltlux_-_luxia-21.4b-alignment-v1.2-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 Alignment v1.2 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Luxia models

All Luxia →

Other medium models

All medium models →