LU

Lusca 33B Q4 K M

LuscaGGUF by win10Updated 2024-09-25
Download on Hugging Face
Parameters33.2B
Context128K
Layers84
Architecturellama
Smallest quant19.9 GB
Quick answer

Lusca 33B Q4 K M needs about 23.2 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 11.3 GB.

Lusca 33B Q4 K M is a 33.2B-parameter Lusca model in GGUF format, quantized by win10. Its trained context length is 128K tokens. The repository has 1 quant file, from 19.9 GB (Q4_K_M) to 19.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.9 GB 23.2 GB
Too big Get file →

What GPU do you need for Lusca 33B Q4 K M?

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: the best quant that fits is Q4_K_M (19.9 GB file, about 23.2 GB in use).

Which Lusca 33B Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Lusca 33B Q4 K M: it balances file size and quality well. Here it is a 19.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.2B
Layers84
Trained context131,072 tokens
KV cache (fp16)336 KB per token

Source

Quantized bywin10
FamilyLusca
Licenseother
Downloads (HF)36
Last updated2024-09-25

Frequently asked questions about Lusca 33B Q4 K M

How much VRAM does Lusca 33B Q4 K M need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Lusca 33B Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lusca 33B Q4 K M GGUF?

It depends on the quant: Q4_K_M is 19.9 GB.

What context length does Lusca 33B Q4 K M support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.8 GB at 8K and 11.3 GB at 32K.

Where can I download Lusca 33B Q4 K M GGUF?

The files are on Hugging Face in the win10/Lusca-33B-Q4_K_M-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 Lusca 33B Q4 K M use?

Hugging Face lists the license as other. 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 Lusca-33B

Similar models

Browse all →

More from win10

All by win10 →

More Lusca models

All Lusca →

Other medium models

All medium models →