kabyul exaone nsmc lora needs about 1.8 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.8 GB (Q4_K_M) to 2.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
kabyul exaone nsmc lora is a 1.28B-parameter Kabyul model in GGUF format, quantized by kopo17. Its trained context length is 64K tokens. The repository has 2 quant files, from 0.8 GB (Q4_K_M) to 2.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.8 GB | 1.8 GB | Fits | Get file → | |
| F16 | 2.6 GB | 3.6 GB | Fits | Get file → |
What GPU do you need for kabyul exaone nsmc lora?
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: the best quant that fits is F16 (2.6 GB file, about 3.6 GB in use).
Which kabyul exaone nsmc lora quant should you choose?
Q4_K_M is the usual starting point for kabyul exaone nsmc lora: it balances file size and quality well. Here it is a 0.8 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kabyul exaone nsmc lora
How much VRAM does kabyul exaone nsmc lora need?
About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.8 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 kabyul exaone nsmc lora on an 8 GB GPU?
Yes, with F16: the 2.6 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kabyul exaone nsmc lora GGUF?
It depends on the quant: Q4_K_M is 0.8 GB, F16 is 2.6 GB.
What context length does kabyul exaone nsmc lora support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.
Where can I download kabyul exaone nsmc lora GGUF?
The files are on Hugging Face in the kopo17/kabyul-exaone-nsmc-lora-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.