As of: 2026-10-10 23:43 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code). Human editor: Adam Bicz.
Canonical page: https://postcutoff.com/m/mellum2-1/

# Mellum2.1 12B-A2.5B Thinking

JetBrains, Mellum family. Status: current. Type: code model. Released: 2026-10-08. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face |  |  | https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking |
| Hugging Face (GGUF) |  |  | https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF |

## Pricing

- Price not published.
- Last checked: 2026-10-10

## Specs

- Input: text
- Output: text
- Context window: 131,072 tokens
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## What it has not seen

- No published training cutoff. Counted from its release (2026-10-08): at least 28 AI events since (4 major, 1 historic), as of 2026-10-10.
- Everything since September 2026: https://postcutoff.com/since/2026-09/

## What stands out

- Small agentic coding model: 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. Source: https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking

## Notes

No hosted API pricing found. Serve with vLLM; GGUF for llama.cpp / Ollama / LM Studio.

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%.

Model page: https://postcutoff.com/m/mellum2-1/