PulseAugur
EN
LIVE 03:23:13
한국어(KO) 오늘의 한국 AI 순위 (2026-11-19): 공인 벤치마크 1위 14개, 다운로드 1위 POCKET-Darwin-180B-GGUF

Korean AI Models: POCKET-Darwin-180B-GGUF Leads Downloads, Vidraft Dominates Benchmarks

A recent ranking of Korean AI models on November 19, 2026, highlights POCKET-Darwin-180B-GGUF as the top downloaded open LLM in South Korea, with over 500,000 downloads in the last 30 days. The report, based on Hugging Face benchmarks and download data, indicates that Korean models lead in 14 benchmark categories. Vidraft's models are particularly dominant, securing first place in 12 of these categories. The ranking also notes shifts in download positions for models like EXAONE-3.5-7.8B-Instruct and Raon-1-mini-preview-gguf. AI

IMPACT Provides insights into the performance and popularity of Korean AI models, influencing developer choices and research directions.

RANK_REASON The item reports on benchmark rankings and download statistics for AI models, which falls under research and product performance. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Korean AI Models: POCKET-Darwin-180B-GGUF Leads Downloads, Vidraft Dominates Benchmarks

How we ranked this

Signal score
43 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item reports on benchmark rankings and download statistics for AI models, which falls under research and product performance. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 한국어(KO) · Vidraft_lab ·

    Today's Korean AI Ranking (2026-11-19): 14 Official Benchmarks Ranked 1st, Download 1st POCKET-Darwin-180B-GGUF

    <h2> 한눈에 보기 (2026-11-19 기준) </h2> <ul> <li>허깅페이스 공인 벤치마크 63개 가운데 순위가 실린 보드는 57개, 등재 결과는 1462건입니다.</li> <li>한국 모델이 1위인 보드는 14개입니다. 그중 비드래프트 모델이 12개 보드에서 1위입니다.</li> <li>한국 오픈 LLM 다운로드 1위는 POCKET-Darwin-180B-GGUF 입니다. 최근 30일 506,502 회입니다.</li> <li>한국 상위 30위 안에 비드래프트 계열 모델이 4개 있습니다.…