LLM Reference

Mellum 2 Models by JetBrains

JetBrainsApache 2.0
1 model2026Up to 131k ctx

About

Mellum 2 is JetBrains' 12B mixture-of-experts model family for software engineering workflows, with 2.5B active parameters per token and long-context support for coding, tool use, reasoning, and agentic work.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

1 in view

Use when the workload needs code, 131k context, and reasoning.

2026-06code131k contextreasoning

Release Timeline

1 release group
2026-06
1 current
Mellum2 12B
code131k contextreasoning
Current

Specifications(1 models)

Mellum 2 model specifications comparison
ModelReleasedContextParametersReasoningFn CallingTool Use
Mellum2 12B2026-06131k12B (2.5B active)YesYesYes

Frequently Asked Questions

What is Mellum 2 used for?
Mellum 2 is used for code, reasoning, and agent workflows and tool use. The family description and listed model capabilities point to those workloads as the best fit.
How does Mellum 2 compare to Mellum?
Mellum 2 by JetBrains is strongest where you need code, while Mellum by JetBrains is the closest related family to check for code. Mellum 2 has 1 listed variant and reaches up to 131k context, while Mellum reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
Which Mellum 2 model should I use?
If price is the main constraint, use the pricing table first because Mellum 2 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Mellum2 12B with 131k context and reasoning, tool use, and function calling.

Models(1)