{"schema":"postcutoff/model@1","as_of":"2026-10-10T23:43:00+02:00","url":"https://postcutoff.com/m/mellum2-1/","md":"https://postcutoff.com/m/mellum2-1/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"mellum2-1","name":"Mellum2.1 12B-A2.5B Thinking","org":"JetBrains","family":"Mellum","released":"2026-10-08","status":"current","type":"code","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":131072,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","url":"https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"},{"provider":"Hugging Face (GGUF)","url":"https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF"}],"capabilities":[{"name":"Small agentic coding model","detail":"12B MoE with 2.5B active parameters scoring 47.0% on SWE-bench Verified (model card), up from 2.0% for Mellum2, after RL in real repositories with shell and file-editing tools.","first":false,"discovered":"launch","source":"https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"}],"entry":"2026-10-08-jetbrains-mellum2-1","notes":"No hosted API pricing found. Serve with vLLM; GGUF for llama.cpp / Ollama / LM Studio.","verified":"2026-10-10","body_md":"JetBrains' open coding model for local sub-agents. Benchmarks (model card): LiveCodeBench v6 82.0%, AIME 25/26 83.3%, GPQA Diamond 64.6%, BFCL v4 62.3%.","page_url":"https://postcutoff.com/m/mellum2-1/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":28,"you_url":null,"briefings":null}