Model Recipes
JetBrains

JetBrains/Mellum2-12B-A2.5B-Thinking

JetBrains' reasoning-augmented code MoE (12B total / 2.5B active) that emits explicit <think> chains for debugging, planning, and agentic coding

69.9 LiveCodeBench v6, 58.4 AIME — fits on a single GPU

moe12B / 2.5B131,072 ctxvLLM nightly+text
Guide