ER

ERNIE 4.5 VL 28B A3B Thinking

ErnieGGUF by ERNIE-CommunityUpdated 2025-12-01
Download on Hugging Face
Parameters43.2B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant86.5 GB
Quick answer

ERNIE 4.5 VL 28B A3B Thinking needs about 87.5 GB of memory at BF16 (a 86.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ERNIE 4.5 VL 28B A3B Thinking is a 43.2B-parameter Ernie model in GGUF format, quantized by ERNIE-Community. Its trained context length is 128K tokens. The repository has 1 quant file, from 86.5 GB (BF16) to 86.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1686.5 GB 87.5 GB
Too big Get file →

What GPU do you need for ERNIE 4.5 VL 28B A3B Thinking?

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 ERNIE 4.5 VL 28B A3B Thinking quant should you choose?

BF16 (86.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters43.2B (approximate, mixture of experts)
Active parameters3B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byERNIE-Community
FamilyErnie
Licenseapache-2.0
Downloads (HF)7
Last updated2025-12-01

Frequently asked questions about ERNIE 4.5 VL 28B A3B Thinking

How much VRAM does ERNIE 4.5 VL 28B A3B Thinking need?

About 87.5 GB at BF16 with an 8K context window. That is the 86.5 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 ERNIE 4.5 VL 28B A3B Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 87.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ERNIE 4.5 VL 28B A3B Thinking GGUF?

It depends on the quant: BF16 is 86.5 GB.

What context length does ERNIE 4.5 VL 28B A3B Thinking 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 VL 28B A3B Thinking GGUF?

The files are on Hugging Face in the ERNIE-Community/ERNIE-4.5-VL-28B-A3B-Thinking-BF16 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 VL 28B A3B Thinking 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 ERNIE-Community

All by ERNIE-Community →

More Ernie models

All Ernie →

Other large models

All large models →