ZE

zelus82 JuliusCesar 72B BeyonderV.0

ZelusGGUF by RichardErkhovUpdated 2024-10-15
Download on Hugging Face
Parameters37.4B
Context32K
Layers40
Architecturellama
Smallest quant4.2 GB
Quick answer

zelus82 JuliusCesar 72B BeyonderV.0 needs about 34.0 GB of memory at Q4_K_M (a 22.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 4.2 GB (IQ4_XS) to 39.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 42.9 GB.

zelus82 JuliusCesar 72B BeyonderV.0 is a 37.4B-parameter Zelus model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 4.2 GB (IQ4_XS) to 39.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS4.2 GB 15.4 GB
Too big Get file →
Q5_K_S10.0 GB 21.2 GB
Too big Get file →
Q2_K14.3 GB 25.5 GB
Too big Get file →
IQ3_XS15.7 GB 27.0 GB
Too big Get file →
IQ3_S16.6 GB 27.8 GB
Too big Get file →
Q3_K_S16.6 GB 27.8 GB
Too big Get file →
IQ3_M17.4 GB 28.6 GB
Too big Get file →
Q3_K18.4 GB 29.6 GB
Too big Get file →
Q3_K_M18.4 GB 29.6 GB
Too big Get file →
Q5_K_M18.4 GB 29.7 GB
Too big Get file →
Q3_K_L20.0 GB 31.3 GB
Too big Get file →
Q4_021.4 GB 32.6 GB
Too big Get file →
IQ4_NL21.5 GB 32.7 GB
Too big Get file →
Q4_K_S21.5 GB 32.8 GB
Too big Get file →
Q4_K22.7 GB 34.0 GB
Too big Get file →
Q4_K_M22.7 GB 34.0 GB
Too big Get file →
Q4_123.6 GB 34.9 GB
Too big Get file →
Q5_025.9 GB 37.1 GB
Too big Get file →
Q5_K26.6 GB 37.8 GB
Too big Get file →
Q5_128.1 GB 39.4 GB
Too big Get file →
Q6_K30.7 GB 41.9 GB
Too big Get file →
Q8_039.7 GB 51.0 GB
Too big Get file →

What GPU do you need for zelus82 JuliusCesar 72B BeyonderV.0?

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 IQ4_XS (4.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_S (10.0 GB file, about 21.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_L (20.0 GB file, about 31.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (30.7 GB file, about 41.9 GB in use).

Which zelus82 JuliusCesar 72B BeyonderV.0 quant should you choose?

Q4_K_M is the usual starting point for zelus82 JuliusCesar 72B BeyonderV.0: it balances file size and quality well. Here it is a 22.7 GB file.

The Q8_0 file is 39.7 GB, about 1.7 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 IQ4_XS at 4.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters37.4B
Layers40
Trained context32,768 tokens
KV cache (fp16)1280 KB per token

Source

Quantized byRichardErkhov
FamilyZelus
Licenseapache-2.0
Downloads (HF)76
Last updated2024-10-15

Frequently asked questions about zelus82 JuliusCesar 72B BeyonderV.0

How much VRAM does zelus82 JuliusCesar 72B BeyonderV.0 need?

About 34.0 GB at Q4_K_M with an 8K context window. That is the 22.7 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 zelus82 JuliusCesar 72B BeyonderV.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of zelus82 JuliusCesar 72B BeyonderV.0 GGUF?

It depends on the quant: IQ4_XS is 4.2 GB, Q5_K_S is 10.0 GB, Q2_K is 14.3 GB, IQ3_XS is 15.7 GB, IQ3_S is 16.6 GB, Q3_K_S is 16.6 GB and 16 more.

What context length does zelus82 JuliusCesar 72B BeyonderV.0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 10.7 GB at 8K and 42.9 GB at 32K.

Where can I download zelus82 JuliusCesar 72B BeyonderV.0 GGUF?

The files are on Hugging Face in the RichardErkhov/zelus82_-_JuliusCesar-72B-BeyonderV.0-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 zelus82 JuliusCesar 72B BeyonderV.0 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 Zelus models

All Zelus →

Other large models

All large models →