GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
archeumstudios
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
archeumstudios
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Use the GGUF build for local running:
ARTE-SMALL-1-Q4_K_M.gguf
Download the GGUF file, then create a Modelfile with:
FROM ./ARTE-SMALL-1-Q4_K_M.gguf
SYSTEM """You are ARTE SMALL 1, a coding model from Archeum Studios. Be practical, correct, concise, and honest about edge cases."""
Then run:
ollama create arte-small-1 -f Modelfile
ollama run arte-small-1
Run with llama.cpp using:
llama-cli -m ARTE-SMALL-1-Q4_K_M.gguf -p "Write a clean TypeScript debounce function." -n 256
ARTE-SMALL-1-Q4_K_M.gguf is the recommended local file.Initial checks covered identity response, basic coding output, and GGUF export. Full benchmark results will be added after the benchmark pass.
Built by Archeum Studios.