KURE v1 needs about 1.7 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 16 quants, from 0.4 GB (Q2_K) to 2.3 GB (F32).
KURE v1 – Korean retrieval embedding model
KURE v1 is a 0.567B parameter BERT‑based model fine‑tuned for Korean text retrieval. It supports Korean and English embeddings and is released under the MIT license. The model was trained on 2,000,000 Korean query‑document pairs with a cached GIST loss.
Good at
- Korean retrieval
- Embedding generation
- Multilingual support
Limits
- No vision support
- Context limited to 8192 tokens
- No active parameters
Best for
- Document similarity search
- Question‑answer retrieval
- Embedding‑based clustering
Who it’s for. Developers building Korean language search or QA systems. Researchers needing a lightweight Korean embedding model for retrieval tasks. Data scientists looking for a MIT‑licensed, easy‑to‑deploy embedding solution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ4_NL | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_0 | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.9 GB | Fits | Get file → | |
| BF16 | 1.2 GB | 2.5 GB | Fits | Get file → | |
| F32 | 2.3 GB | 3.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (0.42 GB file, ~1.7 GB memory). For 16 GB VRAM, Q5_K_M or Q6_K (0.47–0.5 GB file, ~1.8 GB memory) provide higher quality. The BF16 and F32 versions require 2.5–3.6 GB memory and are best for CPU inference or high‑precision needs.
What GPU do you need for KURE v1?
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 F32 (2.3 GB file, about 3.6 GB in use).
Which KURE v1 quant should you choose?
Q4_K_M is the usual starting point for KURE v1: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.4 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 Q2_K at 0.4 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
Source
Frequently asked questions about KURE v1
How much VRAM does KURE v1 need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.4 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 KURE v1 on an 8 GB GPU?
Yes, with F32: the 2.3 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 KURE v1 GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.4 GB, IQ4_XS is 0.4 GB, Q3_K_L is 0.4 GB, Q4_0 is 0.4 GB and 10 more.
What context length does KURE v1 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.
Where can I download KURE v1 GGUF?
The files are on Hugging Face in the mykor/KURE-v1-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 KURE v1 use?
Hugging Face lists the license as mit. 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 KURE v1 on 8 GB VRAM?
Yes, use a Q4 quantization such as Q4_0 or Q4_K_S, which requires about 1.7 GB memory at 8k context.
Does KURE v1 support vision tasks?
No, the model only provides text embeddings and has no vision capabilities.