ernie 4.5 a3b 21b thinking needs about 23.0 GB of memory at its main file (a 22.0 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 4.5 a3b 21b thinking is a 21.8B-parameter Ernie model in GGUF format, quantized by AmpereComputing. Its trained context length is 128K tokens. The repository has 1 quant file, from 22.0 GB to 22.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 22.0 GB | 23.0 GB | Too big | Get file → |
What GPU do you need for ernie 4.5 a3b 21b 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 the main file (22.0 GB file, about 23.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ernie 4.5 a3b 21b thinking
How much VRAM does ernie 4.5 a3b 21b thinking need?
About 23.0 GB at its main file with an 8K context window. That is the 22.0 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 a3b 21b thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ernie 4.5 a3b 21b thinking GGUF?
It depends on the quant: file is 22.0 GB.
What context length does ernie 4.5 a3b 21b 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 a3b 21b thinking GGUF?
The files are on Hugging Face in the AmpereComputing/ernie-4.5-a3b-21b-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 a3b 21b 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.