AP

APUS xDAN 4.0 MOE

ApusGGUF by xDAN2099Updated 2024-04-16
Download on Hugging Face
Parameters114B
Context32K
Layers60
Architecturellama
Smallest quant41.5 GB
Quick answer

APUS xDAN 4.0 MOE needs about 44.0 GB of memory at Q2_K (a 41.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

APUS xDAN 4.0 MOE is a 114B-parameter Apus model in GGUF format, quantized by xDAN2099. Its trained context length is 32K tokens. The repository has 1 quant file, from 41.5 GB (Q2_K) to 41.5 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K41.5 GB 44.0 GB
Too big Get file →

What GPU do you need for APUS xDAN 4.0 MOE?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K (41.5 GB file, about 44.0 GB in use).

Which APUS xDAN 4.0 MOE quant should you choose?

Q2_K (41.5 GB) is the middle option in this repository. 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
Parameters114B (approximate, mixture of experts)
Layers60
Trained context32,768 tokens
KV cache (fp16)240 KB per token

Source

Quantized byxDAN2099
FamilyApus
Licensecc-by-4.0
Downloads (HF)27
Last updated2024-04-16

Frequently asked questions about APUS xDAN 4.0 MOE

How much VRAM does APUS xDAN 4.0 MOE need?

About 44.0 GB at Q2_K with an 8K context window. That is the 41.5 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 APUS xDAN 4.0 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of APUS xDAN 4.0 MOE GGUF?

It depends on the quant: Q2_K is 41.5 GB.

What context length does APUS xDAN 4.0 MOE support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download APUS xDAN 4.0 MOE GGUF?

The files are on Hugging Face in the xDAN2099/APUS-xDAN-4.0-MOE repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does APUS xDAN 4.0 MOE use?

Hugging Face lists the license as cc-by-4.0. 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 Apus models

All Apus →

Other large models

All large models →