Apex Labs · Local AI
Run Apex on your machine
Apex-3B is Wesley's custom local model. Chat online with zero setup, or download the GGUF and load it in LM Studio for fully private offline use.
Apex-3B
Apex-3B-Q4_K_M.gguf
- File size
- ~1.93 GB
- Quantization
- Q4_K_M
- Format
- GGUF
- Suggested RAM
- 8 GB+
Download link not set yet. Wesley will put the Hugging Face URL in config.js
(DOWNLOAD_URL). Until then, grab the GGUF from your Apex Labs release channel.
Model id: imnotapex/Apex-3B
Load in LM Studio
- Install LM Studio Get it from lmstudio.ai for Windows, macOS, or Linux.
-
Import the GGUF
Open LM Studio → My Models → drag in
Apex-3B-Q4_K_M.gguf(or use “Import model”). - Load & start the server Load Apex-3B, open Local Server / Developer, click Start Server, and turn CORS on.
-
Chat
Open the Apex Chat page, set Mode to Local
(API base
http://127.0.0.1:1234/v1), and send a message.
Requirements
- ~2 GB free disk for the Q4_K_M GGUF
- 8 GB+ system RAM recommended (more is better for longer context)
- GPU optional — CPU works; a recent NVIDIA/AMD/Apple GPU speeds things up
- Modern browser for this site; LM Studio for the local OpenAI-compatible API