ER

ERNIE 21B A3B Claude 4.5 High OPUS Thinking

ErnieGGUF by DagowinaUpdated 2026-03-27
Download on Hugging Face
Parameters21.8B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant17.9 GB
Quick answer

ERNIE 21B A3B Claude 4.5 High OPUS Thinking needs about 18.9 GB of memory at Q6_K (a 17.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ERNIE 21B A3B Claude 4.5 High OPUS Thinking is a 21.8B-parameter Ernie model in GGUF format, quantized by Dagowina. Its trained context length is 128K tokens. The repository has 1 quant file, from 17.9 GB (Q6_K) to 17.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K17.9 GB 18.9 GB
Too big Get file →

What GPU do you need for ERNIE 21B A3B Claude 4.5 High OPUS 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: the best quant that fits is Q6_K (17.9 GB file, about 18.9 GB in use).

Which ERNIE 21B A3B Claude 4.5 High OPUS Thinking quant should you choose?

Q6_K (17.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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

Frequently asked questions about ERNIE 21B A3B Claude 4.5 High OPUS Thinking

How much VRAM does ERNIE 21B A3B Claude 4.5 High OPUS Thinking need?

About 18.9 GB at Q6_K with an 8K context window. That is the 17.9 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 A3B Claude 4.5 High OPUS Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ERNIE 21B A3B Claude 4.5 High OPUS Thinking GGUF?

It depends on the quant: Q6_K is 17.9 GB.

What context length does ERNIE 21B A3B Claude 4.5 High OPUS 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 21B A3B Claude 4.5 High OPUS Thinking GGUF?

The files are on Hugging Face in the Dagowina/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking-Q6_K-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 21B A3B Claude 4.5 High OPUS 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.

Other GGUFs of ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking

Similar models

Browse all →

More from Dagowina

All by Dagowina →

More Ernie models

All Ernie →

Other medium models

All medium models →