LGAI EXAONE.K EXAONE 236B A23B needs about 145.6 GB of memory at F16 (a 143.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 86.5 GB (F16) to 252.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.6 GB.
LGAI EXAONE.K EXAONE 236B A23B is a 237B-parameter Exaone model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 6 quant files, from 86.5 GB (F16) to 252.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 86.5 GB (7 parts) | 88.6 GB | Too big | Get file → | |
| F16 | 113.3 GB (9 parts) | 115.5 GB | Too big | Get file → | |
| F16 | 143.5 GB (11 parts) | 145.6 GB | Too big | Get file → | |
| F16 | 168.3 GB (13 parts) | 170.4 GB | Too big | Get file → | |
| F16 | 194.6 GB (15 parts) | 196.8 GB | Too big | Get file → | |
| F16 | 252.0 GB (21 parts) | 254.2 GB | Too big | Get file → |
What GPU do you need for LGAI EXAONE.K EXAONE 236B A23B?
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 LGAI EXAONE.K EXAONE 236B A23B quant should you choose?
F16 (143.5 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.
If memory is tight, the smallest file is F16 at 86.5 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about LGAI EXAONE.K EXAONE 236B A23B
How much VRAM does LGAI EXAONE.K EXAONE 236B A23B need?
About 145.6 GB at F16 with an 8K context window. That is the 143.5 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 LGAI EXAONE.K EXAONE 236B A23B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 88.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LGAI EXAONE.K EXAONE 236B A23B GGUF?
It depends on the quant: F16 is 86.5 GB, F16 is 113.3 GB, F16 is 143.5 GB, F16 is 168.3 GB, F16 is 194.6 GB, F16 is 252.0 GB.
What context length does LGAI EXAONE.K EXAONE 236B A23B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.6 GB at 32K.
Where can I download LGAI EXAONE.K EXAONE 236B A23B GGUF?
The files are on Hugging Face in the DevQuasar/LGAI-EXAONE.K-EXAONE-236B-A23B-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 LGAI EXAONE.K EXAONE 236B A23B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.