XV

XVERSE-13B-256K

XverseGGUF by heimbergleeUpdated 2024-04-21
Download on Hugging Face
Parameters13.7B
Context32K
Layers40
Architecturexverse
Smallest quant8.4 GB
Quick answer

XVERSE-13B-256K needs about 15.6 GB of memory at Q4_K_M (a 8.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

XVERSE-13B-256K is a 13.7B-parameter Xverse model in GGUF format, quantized by heimberglee. Its trained context length is 32K tokens. The repository has 1 quant file, from 8.4 GB (Q4_K_M) to 8.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M8.4 GB 15.6 GB
Too big Get file →

What GPU do you need for XVERSE-13B-256K?

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 (8.4 GB file, about 15.6 GB in use).

Which XVERSE-13B-256K quant should you choose?

Q4_K_M is the usual starting point for XVERSE-13B-256K: it balances file size and quality well. Here it is a 8.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturexverse
Parameters13.7B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byheimberglee
FamilyXverse
Licenseapache-2.0
Downloads (HF)6
Last updated2024-04-21

Frequently asked questions about XVERSE-13B-256K

How much VRAM does XVERSE-13B-256K need?

About 15.6 GB at Q4_K_M with an 8K context window. That is the 8.4 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 XVERSE-13B-256K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of XVERSE-13B-256K GGUF?

It depends on the quant: Q4_K_M is 8.4 GB.

What context length does XVERSE-13B-256K support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download XVERSE-13B-256K GGUF?

The files are on Hugging Face in the heimberglee/XVERSE-13B-256K-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 XVERSE-13B-256K 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 Xverse models

All Xverse →

Other medium models

All medium models →