PL

Plap 8x13B

PlapGGUF by MergeFuelUpdated 2023-12-17
Download on Hugging Face
Parameters72.5B
Context32K
Layers40
Architecturellama
Smallest quant25.5 GB
Quick answer

Plap 8x13B needs about 49.1 GB of memory at Q4_K_M (a 41.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 25.5 GB (Q2_K) to 41.9 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

Plap 8x13B is a 72.5B-parameter Plap model in GGUF format, quantized by MergeFuel. Its trained context length is 32K tokens. The repository has 4 quant files, from 25.5 GB (Q2_K) to 41.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 32.7 GB
Too big Get file →
Q3_K_M32.7 GB 39.9 GB
Too big Get file →
Q4_041.9 GB 49.1 GB
Too big Get file →
Q4_K_M41.9 GB 49.1 GB
Too big Get file →

What GPU do you need for Plap 8x13B?

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 Q3_K_M (32.7 GB file, about 39.9 GB in use).

Which Plap 8x13B quant should you choose?

Q4_K_M is the usual starting point for Plap 8x13B: it balances file size and quality well. Here it is a 41.9 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 GB, with the quality trade-offs that come with fewer bits. 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
Parameters72.5B (approximate, mixture of experts)
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byMergeFuel
FamilyPlap
Downloads (HF)19
Last updated2023-12-17

Frequently asked questions about Plap 8x13B

How much VRAM does Plap 8x13B need?

About 49.1 GB at Q4_K_M with an 8K context window. That is the 41.9 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 Plap 8x13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Plap 8x13B GGUF?

It depends on the quant: Q2_K is 25.5 GB, Q3_K_M is 32.7 GB, Q4_0 is 41.9 GB, Q4_K_M is 41.9 GB.

What context length does Plap 8x13B 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 Plap 8x13B GGUF?

The files are on Hugging Face in the MergeFuel/Plap-8x13B-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 Plap 8x13B use?

Hugging Face lists the license as cc-by-nc-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 from MergeFuel

All by MergeFuel →

More Plap models

All Plap →

Other large models

All large models →