ER

Ernie-4.5-21B-A3B-Thinking

ErnieGGUF by XythicKUpdated 2025-12-03
Download on Hugging Face
Parameters21.8B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant7.1 GB
Quick answer

Ernie-4.5-21B-A3B-Thinking needs about 14.3 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 7.1 GB (IQ1_S) to 43.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Ernie-4.5-21B-A3B-Thinking is a 21.8B-parameter Ernie model in GGUF format, quantized by XythicK. Its trained context length is 128K tokens. The repository has 21 quant files, from 7.1 GB (IQ1_S) to 43.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.1 GB 8.0 GB
Too big Get file →
IQ1_M7.3 GB 8.3 GB
Too big Get file →
IQ2_XXS7.8 GB 8.7 GB
Too big Get file →
IQ2_M8.1 GB 9.0 GB
Too big Get file →
Q2_K8.2 GB 9.2 GB
Too big Get file →
Q2_K_L8.2 GB 9.2 GB
Too big Get file →
Q2_K_XL8.6 GB 9.6 GB
Too big Get file →
IQ3_XXS9.6 GB 10.6 GB
Too big Get file →
Q3_K_S9.6 GB 10.6 GB
Too big Get file →
Q3_K_XL10.1 GB 11.1 GB
Too big Get file →
Q3_K_M10.6 GB 11.5 GB
Too big Get file →
IQ4_XS11.8 GB 12.8 GB
Too big Get file →
IQ4_NL12.5 GB 13.4 GB
Too big Get file →
Q4_012.5 GB 13.5 GB
Too big Get file →
Q4_K_S12.5 GB 13.5 GB
Too big Get file →
Q4_K_M13.3 GB 14.3 GB
Too big Get file →
Q4_113.8 GB 14.7 GB
Too big Get file →
Q5_K_M15.6 GB 16.6 GB
Too big Get file →
Q6_K18.0 GB 18.9 GB
Too big Get file →
Q8_023.2 GB 24.2 GB
Too big Get file →
BF1643.7 GB 44.6 GB
Too big Get file →

What GPU do you need for Ernie-4.5-21B-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: the best quant that fits is IQ1_S (7.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (10.6 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (13.8 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.0 GB file, about 18.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 24.2 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (43.7 GB file, about 44.6 GB in use).

Which Ernie-4.5-21B-A3B-Thinking quant should you choose?

Q4_K_M is the usual starting point for Ernie-4.5-21B-A3B-Thinking: it balances file size and quality well. Here it is a 13.3 GB file.

The Q8_0 file is 23.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 7.1 GB, with the quality trade-offs that come with fewer bits. 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

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 byXythicK
FamilyErnie
Licenseapache-2.0
Downloads (HF)555
Last updated2025-12-03

Frequently asked questions about Ernie-4.5-21B-A3B-Thinking

How much VRAM does Ernie-4.5-21B-A3B-Thinking need?

About 14.3 GB at Q4_K_M with an 8K context window. That is the 13.3 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-Thinking on an 8 GB GPU?

Yes, with IQ1_S: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ernie-4.5-21B-A3B-Thinking GGUF?

It depends on the quant: IQ1_S is 7.1 GB, IQ1_M is 7.3 GB, IQ2_XXS is 7.8 GB, IQ2_M is 8.1 GB, Q2_K is 8.2 GB, Q2_K_L is 8.2 GB and 15 more.

What context length does Ernie-4.5-21B-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-4.5-21B-A3B-Thinking GGUF?

The files are on Hugging Face in the XythicK/ERNIE-4.5-21B-A3B-Thinking-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-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-4.5-21B-A3B-Thinking

Similar models

Browse all →

More from XythicK

All by XythicK →

More Ernie models

All Ernie →

Other medium models

All medium models →