KORMo-VL/KORMo-Web-4B
image-text-to-text model by KORMo-VL
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
KORMo-Web-4B is a 4B vision-language agent that completes real browser tasks from screenshots alone. Give it a request in Korean or English; it plans, clicks, types and moves between sites and tabs until the task is done. In the same live-web evaluation, it beats every open-weight web agent we compared, by +9.6 points in English and +22.1 points in Korean. On Online-Mind2Web it reaches 42.3% in English and 42.3% in Korean, which is +22.3 / +28.8 points over the base Qwen3.5-4B. All models below ran the same 612 live-website tasks (300 English, 312 Korean), each with its own prompt and action format, and were scored by the same LLM judge. Success rate (%). The denominator is always the full task count, so crashed or empty runs count as failures. KORMo-Web-4B outperforms open web agents of similar size in both English and Korean. Tested with vLLM 0.23.0 and transformers 5.12.1. The…
Read the full model card ↗ · Preview checked 2026-11-18T09:48:36.158Z
Inside the original model card — Document outline
- KORMo-Web-4B
- What Makes KORMo-Web Different?
- Performance
- Why KORMo-Web
- Quickstart
- Run the agent
- Inference example (one step)
- How It Works
- Evaluation Details
- Files
- 한국어 요약
- Acknowledgements
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
KORMo-VL/KORMo-Web-4B is a image-text-to-text model repository published by KORMo-VL on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 43
- Cumulative likes
- 48
- Hugging Face trending score
- 39
- Reported safetensors parameters
- 5,174,964,736
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-14T11:22:47.000Z
- Last modified
- 2026-11-17T08:30:22.000Z
Compatibility and lineage
Reported languages: ko, en
Reported base models: Qwen/Qwen3.5-4B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-18T06:59:26.317Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.