naver-hyperclovax models
3 naver-hyperclovax models from naver-hyperclovax on Hugging Face, from 3.7B to 33.3B parameters, published by naver-hyperclovax in F32 and BF16, with a 128K-token context. The smallest official model, HyperCLOVAX-SEED-Vision-Instruct-3B, needs about 16.6 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official naver-hyperclovax size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| HyperCLOVAX-SEED-Vision-Instruct-3B | 3.7B | 16.6 GB | 4.2 GB | 2.1 GB | RTX A5000 | $0.176/hr | 4.0 GB |
| HyperCLOVAX-SEED-Think-14B | 14.7B | 65.9 GB | 16.5 GB | 8.2 GB | A100 | $1.31/hr | 4.8 GB |
| HyperCLOVAX-SEED-Think-32B | 33.3B | 74.5 GB | 37.2 GB | 18.6 GB | A100 | $1.31/hr | 9.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| HyperCLOVAX-SEED-Vision-Instruct-3B | 3.7B | F32 | 16.6 GB | RTX A5000 | $0.176/hr |
| HyperCLOVAX-SEED-Think-14B | 14.7B | F32 | 65.9 GB | A100 | $1.31/hr |
| HyperCLOVAX-SEED-Think-32B | 33.3B | BF16 | 74.5 GB | A100 | $1.31/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.