HyperCLOVAX SEED Vision Instruct 3B needs about 3.6 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
HyperCLOVAX SEED Vision Instruct 3B – lightweight vision‑language model
HyperCLOVAX SEED Vision Instruct 3B is a 3.26B parameter LLaVA‑based model from NAVER. It understands text and images, generating text responses. The model is tuned for Korean language and visual tasks such as VQA and diagram interpretation.
Good at
- Vision‑language inference
- Korean language support
- Efficient inference on modest hardware
Limits
- No vision support on non‑GPU setups
- Requires 8k context for full capability
- License is other, not standard
Best for
- Korean VQA tasks
- Image captioning in Korean
- Lightweight vision‑language demos
Who it’s for. Developers building Korean‑centric vision‑language applications on limited GPU resources. Researchers needing a small, open‑source model for VQA and image understanding.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.0 GB | 3.6 GB | Fits | Get file → |
The only available quant is Q4_K_M with a file size of 2.03 GB. It requires approximately 3.6 GB of VRAM at 8k context, so it fits on GPUs with 8 GB or more. For lower VRAM, no other quant is available.
What GPU do you need for HyperCLOVAX SEED Vision Instruct 3B?
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 Q4_K_M (2.0 GB file, about 3.6 GB in use).
Which HyperCLOVAX SEED Vision Instruct 3B quant should you choose?
Q4_K_M is the usual starting point for HyperCLOVAX SEED Vision Instruct 3B: it balances file size and quality well. Here it is a 2.0 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about HyperCLOVAX SEED Vision Instruct 3B
How much VRAM does HyperCLOVAX SEED Vision Instruct 3B need?
About 3.6 GB at Q4_K_M with an 8K context window. That is the 2.0 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 HyperCLOVAX SEED Vision Instruct 3B on an 8 GB GPU?
Yes, with Q4_K_M: the 2.0 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 HyperCLOVAX SEED Vision Instruct 3B GGUF?
It depends on the quant: Q4_K_M is 2.0 GB.
What context length does HyperCLOVAX SEED Vision Instruct 3B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download HyperCLOVAX SEED Vision Instruct 3B GGUF?
The files are on Hugging Face in the naver-ellm/HyperCLOVAX-SEED-Vision-Instruct-3B-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 HyperCLOVAX SEED Vision Instruct 3B 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.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3.6 GB of VRAM at 8k context, fitting on an 8 GB GPU.
Does it support English text?
The model is tuned for Korean but can process English text; performance may vary.
Is there a CPU inference option?
Inference on CPU is possible via llama.cpp, but performance will be slower and memory usage higher.