Instructions to use Xylolabs/KORMo-Web-11B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Xylolabs/KORMo-Web-11B-MLX-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Xylolabs/KORMo-Web-11B-MLX-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use Xylolabs/KORMo-Web-11B-MLX-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Xylolabs/KORMo-Web-11B-MLX-4bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Xylolabs/KORMo-Web-11B-MLX-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use Xylolabs/KORMo-Web-11B-MLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Xylolabs/KORMo-Web-11B-MLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Xylolabs/KORMo-Web-11B-MLX-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xylolabs/KORMo-Web-11B-MLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use Xylolabs/KORMo-Web-11B-MLX-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Xylolabs/KORMo-Web-11B-MLX-4bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Xylolabs/KORMo-Web-11B-MLX-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Xylolabs/KORMo-Web-11B-MLX-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Xylolabs/KORMo-Web-11B-MLX-4bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Xylolabs/KORMo-Web-11B-MLX-4bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
The language model of KORMo-VL/KORMo-Web-11B (a Llama-style decoder, 10.76B parameters) converted to 4-bit MLX for mlx-lm; the vision tower and image projector of the original are not included.
How to run
pip install mlx-lm==0.32.2
mlx_lm.generate --model Xylolabs/KORMo-Web-11B-MLX-4bit --prompt 'Explain how a heat pump works.'
mlx_lm.chat --model Xylolabs/KORMo-Web-11B-MLX-4bit
Accuracy
Mean KL divergence from BF16 (lower is better) and top-1 agreement with BF16.
| Quant | Size | WikiText-2 KL | top-1 | Chat KL | top-1 | Long-text KL | top-1 |
|---|---|---|---|---|---|---|---|
| MLX 4-bit | 6.56 GB | 0.090664 | 86.946% | 0.134076 | 87.157% | 0.070785 | 87.651% |
| MLX 8-bit | 11.43 GB | 0.000651 | 98.740% | 0.001227 | 98.804% | 0.000587 | 98.900% |
Which file for your hardware
Macs only (MLX runs on Apple silicon; memory options as Apple lists them for the Mac Studio, M5 Max 36, 48, 64 and 128 GB, M5 Ultra 96, 256 and 512 GB, and the 14-inch MacBook Pro M5 Max, checked 2026-11-22). The GPU may use about 75% of unified memory by default; sudo sysctl iogpu.wired_limit_mb=<MB> raises that limit (it resets at reboot). Fit rule: file + KV cache at the stated context + about 2 GB must fit in the GPU limit; sizes in GB (10^9 bytes); context is the longest that fits at the default limit, at least 32K. KV cache 164 KB per token (40 layers x 8 KV heads x 128 x 2 x 2 bytes). No MLX speed has been measured on these Macs.
| Hardware | Memory | Recommended file (ours only) | Context that fits | Notes |
|---|---|---|---|---|
| Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 32-core GPU) | 36 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
80K | Fits at the default GPU limit (75% of memory). Raising it to 90% (sudo sysctl iogpu.wired_limit_mb=33177) allows 113K. |
| Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 40-core GPU) | 48 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
| Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 40-core GPU) | 64 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
| Mac Studio M5 Ultra | 96 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
| Mac Studio M5 Max, 40-core GPU (also MacBook Pro 14-inch) | 128 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
| Mac Studio M5 Ultra | 256 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
| Mac Studio M5 Ultra, 80-core GPU | 512 GB unified | Xylolabs/KORMo-Web-11B-MLX-8bit (8-bit, 11.43 GB) |
128K (model maximum) | Fits at the default GPU limit (75% of memory). |
License and notices
The base model declares the Apache License 2.0 in its model card; its repository ships no license file, so LICENSE holds the standard Apache License 2.0 text. We converted the language-model weights to MLX 4-bit and renamed the two per-layer norm tensors to Llama's names so mlx-lm loads the model as llama; the vision tower and projector are left out. The source revision and changes are in ORIGINS.md and NOTICE. Not affiliated with or endorsed by KAIST MLP Lab.
Updates
- 2026-11-22: Added a hardware recommendation table.
- 2026-11-22: First release.
KORMo's original model description
Below is the model card of KORMo-VL/KORMo-Web-11B (Apache-2.0), without its metadata header and unchanged.
KORMo-Web-11B
One Model. Three Capabilities: LLM, VLM, and Web Agent.
KORMo-Web-11B는 KAIST MLP 연구실이 처음부터 구축한 KORMo 파운데이션 모델을 기반으로, LLM·VLM·GUI Agent 능력을 모두 갖춘 범용 멀티모달 AI 모델입니다.
- 하나의 모델, 세 가지 능력: 일반적인 질문에는 LLM으로 답변하고, 이미지 이해가 필요한 경우 VLM으로, 웹 조작이 필요한 요청에는 GUI Agent로 작동합니다.
- 독자 파운데이션 모델 기반: From-scratch로 학습한 KORMo-10B를 KORMo-VL로 확장하고, 기존 언어·시각 이해 능력을 유지하도록 학습한 웹 에이전트로 생각<Think> 또한 유일하게 한국어로 하는 모델입니다.
- 대규모 웹 사전학습: 1,000만 건 이상의 한영 웹 학습 샘플로 UI 요소의 위치·의미·구조·기능 등을 세밀하게 학습했습니다.
- 실제 웹 행동 학습: 10만 건 이상의 한영 웹 사용 궤적을 활용해 복잡한 다단계 웹 작업을 수행합니다.
- 완전 공개 및 상업적 활용: 모델 가중치와 학습·평가 리소스를 공개하며, Apache-2.0 라이선스에 따라 상업적 이용과 수정·재배포가 가능합니다.
KORMo-Web-11B is a general-purpose bilingual AI model built on the KORMo foundation model family, developed by KAIST MLP Lab starting from a language model trained entirely from scratch. Unlike our Qwen-based KORMo-Web-4B and 9B models, which focus on maximizing web task performance, KORMo-Web-11B is designed to preserve its original LLM and VLM capabilities while learning to act as a GUI agent. It can understand Korean and English text, interpret images, and complete real browser tasks by visually navigating webpages—all within a single model.
What Makes KORMo-Web-11B Different?
- Built on Our Own Foundation Model: Developed from the KORMo-10B language model, trained from scratch by KAIST MLP Lab, and extended through KORMo-VL into a web agent.
- Three Capabilities in One Model: Designed to retain general LLM reasoning and VLM understanding while adding GUI interaction capabilities, rather than optimizing exclusively for web navigation.
- 10M+ Atomic-Level Web Pretraining Samples: Large-scale Korean and English web understanding training, covering individual UI elements, their locations, layouts, functions, and states.
- 100K+ Web Interaction Trajectories: Bilingual browser demonstrations for learning real-world, multi-step web tasks.
- Open and Commercially Usable: Model weights and supporting resources are openly released under Apache-2.0, allowing commercial use, modification, and redistribution subject to the license terms.
From a Korean LLM to a General-Purpose Web Agent
KORMo-Web-11B extends our independently developed Korean–English foundation model through three stages:
| Stage | Model | Capabilities |
|---|---|---|
| 1. Language | KORMo-10B | Korean–English LLM trained from scratch with a Korean-optimized tokenizer |
| 2. Vision | KORMo-VL | Multimodal understanding through a SigLIP vision encoder and KORMo language backbone |
| 3. Web Agent | KORMo-Web-11B | Large-scale web pretraining and action learning for visual browser interaction |
The goal is not just a better web agent, but a versatile model that can understand language, interpret visual information, and interact with the web.
Performance
We evaluated KORMo-Web-11B on 612 live-website tasks (300 English, 312 Korean) from Online-Mind2Web, using the same LLM judge across all evaluated models.
| Model | Size | Online-Mind2Web EN | Online-Mind2Web KO |
|---|---|---|---|
| Qwen3.5-9B (base) | 9B | 24.7 | 16.7 |
| Fara-1.5-4B | 4B | 20.7 | 7.7 |
| UI-TARS-1.5-7B | 7B | 22.3 | 20.2 |
| OpenWebRL-4B | 4B | 32.7 | 15.4 |
| KORMo-Web-11B (ours) | 11B | 31.3 | 33.7 |
| GPT-6-luna (proprietary) | – | 63.0 | 65.7 |
Success rates are calculated over the full task set, including failed or incomplete runs. Each agent uses its own prompt and action format.
KORMo-Web-11B achieves 33.7% Korean task success, exceeding the strongest non-KORMo open-weight baseline listed above by 13.5 percentage points.
While our specialized KORMo-Web-4B and 9B models achieve higher web task success, KORMo-Web-11B prioritizes versatility across language, vision, and GUI interaction, rather than web-only optimization.
Why KORMo-Web-11B?
- Korean from the Ground Up: Built upon our independently pretrained Korean–English foundation model.
- General-Purpose Multimodal AI: Supports text-based language tasks, visual understanding, and browser interactions within one model.
- Visual-First Web Interaction: Operates primarily through screenshots without requiring full DOM or accessibility trees.
- Think, Then Act: Generates an inspectable reasoning step before executing browser actions.
- Commercial Use Permitted: Released under Apache-2.0, supporting academic research, commercial applications, fine-tuning, and redistribution.
- Open and Ready to Run: Includes model weights, Transformers 5 support, a vLLM inference path, browser harness, and reference inference settings.
KORMo-Web-11B — From a Korean Foundation Model to a General-Purpose Web Agent.
How to Start: Chrome Extension
The fastest way to try KORMo-Web is the KORMo-Web Chrome extension: type a request in Chrome's side panel and watch the agent work in your own browser. This video walks through the whole setup, from serving the model to running a task and controlling it from Discord.
Setup guide (about 15 min, Korean narration). Parts that showed account tokens have been blurred.
1. Serve the model on a Mac or on an NVIDIA GPU.
Mac (Apple silicon)
KORMo-Web-11B is served with vLLM on an NVIDIA GPU (see below); a Mac setup for 11B has not been tested. To try KORMo-Web on a Mac, run KORMo-Web-4B or KORMo-Web-9B with vllm-mlx 0.6.0 or later. Pick the one that fits your Mac's memory:
| Model | Weights | Memory in use | Recommended Mac memory |
|---|---|---|---|
KORMo-Web-4B-mlx-4bit (4-bit) |
2.8 GB | about 3.8 GB | 16 GB or more |
KORMo-Web-4B (bf16) |
9.6 GB | about 9.5 GB | 24 GB or more |
KORMo-Web-9B (bf16) |
17.5 GB | about 19 GB | 48 GB or more (32 GB is tight) |
uv venv --python 3.12 && source .venv/bin/activate
uv pip install "vllm-mlx>=0.6.0" huggingface_hub
MODEL=KORMo-Web-4B-mlx-4bit # or KORMo-Web-4B / KORMo-Web-9B
hf download KORMo-VL/$MODEL --local-dir ~/models/$MODEL
vllm-mlx serve ~/models/$MODEL --port 8010 --served-model-name KORMo-VL/$MODEL \
--enable-auto-tool-choice --tool-call-parser auto
Keep this terminal open. --served-model-name is the name the extension must request.
NVIDIA GPU (local PC or server)
vLLM needs a one-time conversion for the KORMo architecture: follow steps 1 and 2 of Run the agent (vLLM) in the Quickstart below, which serve the model as KORMo-Web-11B on port 8000.
Check that it is up with curl http://localhost:8010/v1/models (Mac) or curl http://<server>:8000/v1/models (vLLM). If you changed the port, use that port.
2. Install the extension. git clone https://github.com/MLP-Lab/KORMo-Web-Extension.git, open chrome://extensions, turn on Developer mode, click Load unpacked and choose the cloned folder. Open the GUI 에이전트 side panel, type a task and press 실행 (Run).
3. Point the extension at your model. Open the panel's 개발자 설정 (Developer settings).
- Mac: keep the server URL
http://localhost:8010/v1andtool_choiceauto. Set the model name to your--served-model-name(the defaultKORMo-VL/KORMo-Web-4B-mlx-4bitalready matches the 4-bit build). - NVIDIA GPU: set the server URL to
http://<server>:8000/v1(orlocalhost), the model name toKORMo-Web-11B, andtool_choicetonone.
4. Discord (optional). Run node relay/discord-relay.mjs in the cloned folder and follow the prompts to send tasks to the agent by mentioning a bot in a channel.
Full step-by-step instructions (Korean) are in the extension README.
Quickstart
Tested with transformers 5.12.1 and vLLM 0.23.0. The model runs on a single GPU.
transformers does not ship the KORMo text model, so this repo includes it (_modeling_kormo.py) together with a small loader, kormo_load.py:
kormo_load.register(path)registers the KORMo text model. Call it before loading the processor or the model.kormo_load.patch_vision(model)feeds the SigLIP features after post-layernorm to the projector, as in training. Without it the model still runs but misreads screenshots.
Inference example (one step, transformers)
pip install -U "transformers>=5.12" torch pillow huggingface_hub
hf download KORMo-VL/KORMo-Web-11B --local-dir KORMo-Web-11B
import json, sys, torch
from PIL import Image
from transformers import AutoModelForImageTextToText, AutoProcessor
M = "KORMo-Web-11B"
sys.path.insert(0, M)
import kormo_load
kormo_load.register(M)
processor = AutoProcessor.from_pretrained(M)
model = AutoModelForImageTextToText.from_pretrained(M, dtype=torch.bfloat16).to("cuda").eval()
kormo_load.patch_vision(model)
SYSTEM = open(f"{M}/system_prompt.md").read().strip()
TOOLS = json.load(open(f"{M}/tools.json"))
obs = ("<observation>\nscreen size: 1280 x 720\nCurrent tab: 0\nAvailable tabs:\n"
"- Tab 0 (active): https://www.aladin.co.kr/\n\nurl: https://www.aladin.co.kr/\nscreenshot:\n")
messages = [
{"role": "system", "content": SYSTEM},
{"role": "user", "content": [
{"type": "text", "text": "<user_request>\n알라딘 사이트에서 '해커스 토익 RC'를 검색한 뒤 가장 먼저 표시되는 도서의 출간일을 알려줘.\n</user_request>\n" + obs},
{"type": "image", "image": Image.open("screen.png").convert("RGB")},
{"type": "text", "text": "\n</observation>"},
]},
]
inputs = processor.apply_chat_template(messages, tools=TOOLS, add_generation_prompt=True,
tokenize=True, return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=16384, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)
print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
A real first step from our Online-Mind2Web run (Aladin home page):
<think>I see the Aladin homepage, with the search field labeled “통합검색” near the top. I have not yet searched for the book, so I still need to enter “해커스 토익 RC,” inspect the first result’s publication date, and report that date. My plan:
1. Click the search field
2. Enter “해커스 토익 RC” and submit the search
3. Read the publication date of the first listed book
This click targets the visible search field and is a safe, relevant first action.
</think>
<tool_call>
<function=click>
<parameter=x>
482
</parameter>
<parameter=y>
212
</parameter>
</function>
</tool_call>
Coordinates are normalized to 0–1000. Convert them to pixels with x / 1000 × width and y / 1000 × height.
Run the agent (vLLM)
vLLM does not include the KORMo architecture either. The KORMo text layers have the Llama structure, so vllm/convert_to_vllm.py renames two parameter names and writes a folder vLLM loads natively. vllm/sitecustomize.py turns SigLIP post-layernorm back on inside vLLM.
1. Convert (once)
pip install -U "vllm>=0.23.0" openai playwright safetensors
playwright install chromium
python KORMo-Web-11B/vllm/convert_to_vllm.py KORMo-Web-11B KORMo-Web-11B-vllm
2. Start the model server
PYTHONPATH=$PWD/KORMo-Web-11B/vllm vllm serve ./KORMo-Web-11B-vllm --served-model-name KORMo-Web-11B \
--max-model-len 65536 --limit-mm-per-prompt '{"image":1,"video":0}'
Check that the server log prints [kormo-vllm] SigLIP post_layernorm enabled.
3. Run a browser task
python KORMo-Web-11B/examples/agent_playwright.py --model KORMo-Web-11B \
--start-url https://www.danawa.com/ \
--task "다나와에서 50만 원 이하, 10인치 이상 태블릿 3개를 찾아서 가격을 알려줘"
The agent drives a headless Chromium, prints each action as it goes, and finishes with the model's answer. Add --headful to watch the browser window. The script sends tool_choice="none", which vLLM needs: the tool schema stays in the prompt and the call comes back as text (sending tools without tool_choice returns HTTP 400 unless the server was started with --enable-auto-tool-choice).
How It Works
user <user_request> task </user_request> + observation (tabs, url, screenshot)
assistant <think> what I see · what is done · plan </think> <tool_call> one action </tool_call>
tool action result + new observation (newest screenshot only)
… repeat until finished(answer)
- Action space: 22 browser tools: click, type, hotkey, scroll, drag, goto, tab control,
finished, and others (tools.json). - Memory: the full text history of thoughts, actions and observations is kept. Only the current screenshot is sent.
- Recommended settings: temperature 0.6, top_p 0.95, top_k 20, thinking on, up to 16k tokens per step and 50 steps. These are already set in
generation_config.json.
The exact message format, parsing rules and feedback strings are in HARNESS.md. Follow it if you build your own harness.
Evaluation Details
| Tasks | Online-Mind2Web: 300 English, 312 Korean |
| Judge | GPT-6 |
Files
| File | Description |
|---|---|
model.safetensors · config.json |
Weights and config (LLaVA-OneVision: SigLIP + KORMo-10B text model) |
_configuration_kormo.py · _modeling_kormo.py |
KORMo text model code for transformers 5 |
kormo_load.py |
register() and patch_vision() |
chat_template.jinja |
Chat template (XML tool calls, thinking on) |
system_prompt.md · tools.json |
System prompt and 22-tool schema |
HARNESS.md |
Full harness specification |
examples/agent_playwright.py |
Reference browser agent (Playwright + OpenAI-compatible API). --tool-choice none for vLLM (default); --headful shows the browser. It does not execute upload. |
vllm/convert_to_vllm.py · vllm/sitecustomize.py |
Convert for vLLM and the post-layernorm fix |
generation_config.json · *processor_config.json · tokenizer*.json · special_tokens_map.json |
Sampling, processor and tokenizer configs |
Acknowledgements
Built on KORMo-VL and KORMo-10B by KAIST MLP Lab. Evaluated on Online-Mind2Web and its Korean counterpart.
Contact
- KyungTae Lim, Professor at KAIST.
ktlim@kaist.ac.kr
Contributor
- Hangyeol Yoo (hg.yoo@kaist.ac.kr)
- Minkyu Kim (minkyukim@kaist.ac.kr)
- Minkyung Cho (minkyung.cho@kaist.ac.kr)
- Yerin Nam (yerinnam@kaist.ac.kr)
- Seungwoo Song (sswoo@kaist.ac.kr)
- Gyun Lee (gyunini@kaist.ac.kr)
- KyungTae Lim (ktlim@kaist.ac.kr)
- Downloads last month
- 9
4-bit