BI

BigPlap 8x20B

BigplapGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters112B
Context32K
Layers62
Architecturellama
Smallest quant43.6 GB
Quick answer

BigPlap 8x20B needs about 54.5 GB of memory at Q2_K (a 43.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 43.6 GB (Q2_K) to 48.2 GB (IQ3_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 41.6 GB.

BigPlap 8x20B is a 112B-parameter Bigplap model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 2 quant files, from 43.6 GB (Q2_K) to 48.2 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K43.6 GB 54.5 GB
Too big Get file →
IQ3_XS48.2 GB 59.1 GB
Too big Get file →

What GPU do you need for BigPlap 8x20B?

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: no quant fits at an 8K context.

Which BigPlap 8x20B quant should you choose?

Q2_K (43.6 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
Parameters112B (approximate, mixture of experts)
Layers62
Trained context32,768 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
FamilyBigplap
Downloads (HF)18
Last updated2024-12-16

Frequently asked questions about BigPlap 8x20B

How much VRAM does BigPlap 8x20B need?

About 54.5 GB at Q2_K with an 8K context window. That is the 43.6 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 BigPlap 8x20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BigPlap 8x20B GGUF?

It depends on the quant: Q2_K is 43.6 GB, IQ3_XS is 48.2 GB.

What context length does BigPlap 8x20B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 10.4 GB at 8K and 41.6 GB at 32K.

Where can I download BigPlap 8x20B GGUF?

The files are on Hugging Face in the mradermacher/BigPlap-8x20B-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 BigPlap 8x20B 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.

Other GGUFs of BigPlap-8x20B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bigplap models

All Bigplap →

Other large models

All large models →