Tae-Ho Kim

ktho22's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 5 days ago

Efficient Qwen Family

Collection

3 items • Updated 7 days ago • 1

liked 2 models 5 days ago

nota-ai/Qwen3.5-122B-A10B-NotaCompression-INT4

Text Generation • 22B • Updated Jun 29 • 234 • 1

nota-ai/Qwen3.8-2.4T-A95B-Nota-NVFP4-Global-Pruned-40

Text Generation • 1.5T • Updated 7 days ago • 431 • 23

liked a model 12 days ago

nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15

Text Generation • 16B • Updated 9 days ago • 875 • 20

upvoted a collection 12 days ago

Efficient NVIDIA Models

Collection

Compressed NVIDIA Models (Nemotron and Cosmos) • 1 item • Updated 7 days ago • 1

liked 2 models 23 days ago

nota-ai/Kimi-K3-Nota-Global-Pruned-50

Image-Text-to-Text • 1.4T • Updated 24 days ago • 2.19k • 15

nota-ai/Kimi-K3-Nota-Global-Pruned-25

Image-Text-to-Text • 2.1T • Updated 24 days ago • 152 • 10

upvoted a collection 23 days ago

Efficient Kimi Family

Collection

Optimized Kimi models • 2 items • Updated 24 days ago • 2

upvoted a collection 28 days ago

Efficient Solar Open Family

Collection

Solar Open models officially optimized by Nota AI for Korea’s government-led Sovereign AI initiative as part of the Upstage consortium. • 7 items • Updated Jul 23 • 26

liked 5 models about 1 month ago

nota-ai/Solar-Open2-250B-Nota-NVFP4-GlobalPruned

Text Generation • 117B • Updated 19 days ago • 545 • 34

nota-ai/Solar-Open2-250B-Nota-NVFP4

Text Generation • 145B • Updated 19 days ago • 69.2k • 174

nota-ai/Solar-Open2-250B-Nota-INT4

Text Generation • 41B • Updated Jul 23 • 6.05k • 40

nota-ai/Solar-Open2-250B-Nota-INT4-GlobalPruned

Text Generation • 35B • Updated 26 days ago • 657 • 43

upstage/Solar-Open2-250B

Text Generation • 250B • Updated 25 days ago • 35.4k • 749

upvoted a paper about 1 month ago

Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B

Paper • 2607.04244 • Published Jul 5 • 1

upvoted 2 collections 6 months ago

Efficient MoE-based LLM

Collection

Mixture-of-Experts Large Language Models with Advanced Quantization • 5 items • Updated Mar 11 • 25

Efficient Large Vision-Language Model

Collection

ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO • 3 items • Updated Feb 22 • 27

liked 2 models 7 months ago

nota-ai/Solar-Open-100B-NotaMoEQuant-Int4

Text Generation • 2B • Updated Jan 26 • 646 • 62

nota-ai/Solar-Open-100B-Nota-FP8

Text Generation • 103B • Updated Jan 26 • 284 • 46

liked a model 8 months ago

nota-ai/ERGO-7B

Image-Text-to-Text • 8B • Updated Feb 25 • 21 • 15