Mellum 2.1 Local Test | Open Weight MoE Model by JetBrains | 16GB Local Setup

JetBrains says Mellum 2.1 is made for agentic work, but can it pass a simple car wash prompt? I ran the 12B MoE through llama.cpp and tested it on DaBench (requred ~14GB VRAM). Let's look at the results! DaBench run: https://dabench.ai/model/mellum-2-1-12b-a-2-5b-thinking Weights: https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF AI Academy: https://MLExpert.io Work with me: https://mlexpert.io/consulting DaBench (open weight LLM benchmarks): https://dabench.ai LinkedIn: https://www.linkedin.com/in/venelin-valkov Follow me on X: https://twitter.com/venelin_valkov Discord: ht