ER

ERNIE 4.5 21B A3B PT

ErnieGGUF by fernandoruizUpdated 2025-07-18
Download on Hugging Face
Parameters21.8B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant12.4 GB
Quick answer

ERNIE 4.5 21B A3B PT needs about 13.3 GB of memory at Q4_0 (a 12.4 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 1.9 GB.

ERNIE 4.5 21B A3B PT – 21.8B parameter MoE model in GGUF format

ERNIE 4.5 21B A3B PT is a 21.8B parameter mixture of experts model converted to GGUF. It supports a 131072 token context and is released under the apache-2.0 license.

Good at

  • Large context handling
  • MoE-based inference
  • Text generation

Limits

  • No vision support
  • Requires 13.3 GB VRAM at 8 k context
  • Single quant available

Best for

  • Long-form content creation
  • Complex question answering
  • Research prototyping

Who it’s for. Engineers and researchers needing a large MoE model with extended context. Suitable for environments that can host the 12.36 GB GGUF file and provide the required VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_012.4 GB 13.3 GB
Too big Get file →

The only available quant is Q4_0, 12.36 GB file size. It requires about 13.3 GB VRAM at 8 k context. For lower VRAM budgets, a different model would be needed.

What GPU do you need for ERNIE 4.5 21B A3B PT?

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_0 (12.4 GB file, about 13.3 GB in use).

Which ERNIE 4.5 21B A3B PT quant should you choose?

Q4_0 (12.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters21.8B (approximate, mixture of experts)
Active parameters3B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byfernandoruiz
FamilyErnie
Licenseapache-2.0
Downloads (HF)765
Last updated2025-07-18

Frequently asked questions about ERNIE 4.5 21B A3B PT

How much VRAM does ERNIE 4.5 21B A3B PT need?

About 13.3 GB at Q4_0 with an 8K context window. That is the 12.4 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 ERNIE 4.5 21B A3B PT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ERNIE 4.5 21B A3B PT GGUF?

It depends on the quant: Q4_0 is 12.4 GB.

What context length does ERNIE 4.5 21B A3B PT 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 4.5 21B A3B PT GGUF?

The files are on Hugging Face in the fernandoruiz/ERNIE-4.5-21B-A3B-PT-Q4_0-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 ERNIE 4.5 21B A3B PT 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.

Can I run this model on 8 GB VRAM?

No, the Q4_0 quant requires approximately 13.3 GB VRAM at 8 k context, which exceeds 8 GB.

What license applies to this model?

The model is released under the apache-2.0 license.

Does this model support vision tasks?

No, the model does not support vision modalities.

Other GGUFs of ERNIE-4.5-21B-A3B-PT

Similar models

Browse all →

More from fernandoruiz

All by fernandoruiz →

More Ernie models

All Ernie →

Other medium models

All medium models →