ER

ERNIE 4.5 21B A3B PT

ErnieGGUF by lmstudio-communityUpdated 2025-07-17
Download on Hugging Face
Parameters21.8B
Context128K
Layers28
Architectureernie4_5-moe
Smallest quant10.7 GB
Quick answer

ERNIE 4.5 21B A3B PT needs about 14.5 GB of memory at Q4_K_M (a 13.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 10.7 GB (Q3_K_L) to 23.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

ERNIE 4.5 21B A3B PT – a 21.8B parameter MoE LLM

ERNIE 4.5 21B A3B PT is a text‑only mixture‑of‑experts model with 21.8B total parameters and 3B active parameters. It was trained on 131072 context tokens and released under the Apache‑2.0 license. The model is available in several GGUF quantizations.

Good at

  • Large‑context text generation
  • Mixture‑of‑experts inference
  • Transformer‑style PyTorch weights

Limits

  • No vision support
  • Requires >11.6 GB VRAM for Q3_K_L
  • Licensed under Apache‑2.0

Best for

  • Long‑form content creation
  • Complex text analysis
  • Research prototyping

Who it’s for. Developers and researchers who need a large‑parameter MoE LLM for text tasks and can provide sufficient GPU memory. The model is suitable for environments that support llama.cpp quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L10.7 GB 11.6 GB
Too big Get file →
Q4_K_M13.5 GB 14.5 GB
Too big Get file →
Q6_K18.1 GB 19.1 GB
Too big Get file →
Q8_023.2 GB 24.2 GB
Too big Get file →

For 12 GB VRAM use Q3_K_L (10.66 GB file, 11.6 GB memory). For 16 GB VRAM use Q4_K_M (13.5 GB file, 14.5 GB memory). Higher precision quants require more memory.

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: the best quant that fits is Q3_K_L (10.7 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.5 GB file, about 14.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.1 GB file, about 19.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 24.2 GB in use).

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

Q4_K_M is the usual starting point for ERNIE 4.5 21B A3B PT: it balances file size and quality well. Here it is a 13.5 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 Q3_K_L at 10.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 bylmstudio-community
FamilyErnie
Licenseapache-2.0
Downloads (HF)1,979
Last updated2025-07-17

Frequently asked questions about ERNIE 4.5 21B A3B PT

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

About 14.5 GB at Q4_K_M with an 8K context window. That is the 13.5 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 21B A3B PT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 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: Q3_K_L is 10.7 GB, Q4_K_M is 13.5 GB, Q6_K is 18.1 GB, Q8_0 is 23.2 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 lmstudio-community/ERNIE-4.5-21B-A3B-PT-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 on 8 GB VRAM?

No, the smallest quant requires 11.6 GB of VRAM at 8k context.

Does this model support vision?

No, it is a text‑only model.

What license applies?

Apache‑2.0.

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

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Ernie models

All Ernie →

Other medium models

All medium models →