by Naver
HyperCLOVAX-SEED-Think-14B-GPTQ is a 4-bit quantized version of Naver’s HyperCLOVAX-SEED-Think-14B, a 14B-parameter causal language model optimized for Korean and English conversational tasks. Quantized using GPTQ (W4A16g128), it retains strong performance (e.g., MMLU: 0.7018, HAERAE: 0.8139) while reducing computational and memory requirements. Developed by K-Compression (quantization) and Naver HyperCLOVA (base model), it is licensed under Naver’s proprietary HyperCLOVA X SEED Model License Agreement and is ideal for cost-effective deployment in multilingual applications. Requires GPU support for inference.
Complete information about the vendor/provider of this AI application
Legal, privacy, and compliance documentation
Get insights into risk by running assessments on this AI application.
Discover EU-based alternatives for this AI application.
Track, assess, and govern your AI applications with Anove.
