LL

Luminia 13B v3

LlamaGGUF by NekochuUpdated 2024-03-20
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant6.3 GB
Quick answer

Luminia 13B v3 needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 6.3 GB (Q3_K_M) to 7.9 GB (Q4_K_M).

Luminia 13B v3 is a 13B-parameter Llama model in GGUF format, quantized by Nekochu. Its trained context length is 4K tokens. The repository has 4 quant files, from 6.3 GB (Q3_K_M) to 7.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
IQ4_NL7.4 GB 11.3 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →

What GPU do you need for Luminia 13B v3?

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: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).

Which Luminia 13B v3 quant should you choose?

Q4_K_M is the usual starting point for Luminia 13B v3: it balances file size and quality well. Here it is a 7.9 GB file.

If memory is tight, the smallest file is Q3_K_M at 6.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byNekochu
FamilyLlama
Licenseapache-2.0
Downloads (HF)194
Last updated2024-03-20

Frequently asked questions about Luminia 13B v3

How much VRAM does Luminia 13B v3 need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Luminia 13B v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Luminia 13B v3 GGUF?

It depends on the quant: Q3_K_M is 6.3 GB, IQ4_NL is 7.4 GB, Q4_K_S is 7.4 GB, Q4_K_M is 7.9 GB.

What context length does Luminia 13B v3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Luminia 13B v3 GGUF?

The files are on Hugging Face in the Nekochu/Luminia-13B-v3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Luminia 13B v3 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 Llama-2-13b-chat-hf

Similar models

Browse all →

More from Nekochu

All by Nekochu →

More Llama models

All Llama →

Other medium models

All medium models →