ER

ERNIE 21B REAP GGUFS

ErnieGGUF by jerrimuUpdated 2026-01-26
Download on Hugging Face
Parameters18B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant6.7 GB
Quick answer

ERNIE 21B REAP GGUFS needs about 11.9 GB of memory at its main file (a 10.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 6.7 GB to 36.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ERNIE 21B REAP GGUFS is a 18B-parameter Ernie model in GGUF format, quantized by jerrimu. Its trained context length is 128K tokens. The repository has 3 quant files, from 6.7 GB to 36.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.7 GB 7.6 GB
Tight Get file →
—10.9 GB 11.9 GB
Too big Get file →
—36.0 GB 37.0 GB
Too big Get file →

What GPU do you need for ERNIE 21B REAP GGUFS?

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: the best quant that fits is the main file (6.7 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 11.9 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 11.9 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 11.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (36.0 GB file, about 37.0 GB in use).

Which ERNIE 21B REAP GGUFS quant should you choose?

If memory is tight, the smallest file is the first one in the table at 6.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters18B (approximate, mixture of experts)
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byjerrimu
FamilyErnie
Licenseapache-2.0
Downloads (HF)21
Last updated2026-01-26

Frequently asked questions about ERNIE 21B REAP GGUFS

How much VRAM does ERNIE 21B REAP GGUFS need?

About 11.9 GB at its main file with an 8K context window. That is the 10.9 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 ERNIE 21B REAP GGUFS on an 8 GB GPU?

Yes, with the smaller files: the 6.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ERNIE 21B REAP GGUFS GGUF?

It depends on the quant: file is 6.7 GB, file is 10.9 GB, file is 36.0 GB.

What context length does ERNIE 21B REAP GGUFS support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download ERNIE 21B REAP GGUFS GGUF?

The files are on Hugging Face in the jerrimu/ERNIE-21B-REAP-GGUFS repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ERNIE 21B REAP GGUFS 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 jerrimu

All by jerrimu →

More Ernie models

All Ernie →

Other medium models

All medium models →