Mellum2.1 12B-A2.5B Thinking
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%.
PricePrice not published
Checked10 October 2026
Where it stands
1newer code model since its release
- Recursive Flint21 Oct 2026
- Weights
- Weights are public under a permissive licence (Apache-2.0).
How to call it
2 ways to use Mellum2.1 12B-A2.5B Thinking.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | huggingface.co | ||
| Hugging Face (GGUF) | huggingface.co |
Pricing
Price not published.
No price source linked. Checked 10 October 2026.
Specs
- Input
- Text
- Output
- Text
- Context window
- 131,072 tokens
- Max output
- Not published
- Open weights
- Yes
- Licence
- Apache-2.0
- Released
- 8 October 2026
- Status
- Current
- Type
- Code model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
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.
Notes
No hosted API pricing found. Serve with vLLM; GGUF for llama.cpp / Ollama / LM Studio.