Mellum Models by JetBrains
JetBrainsApache 2.0
1 model2025Up to 8k ctx
About
Mellum is JetBrains' open-weights 4B code-completion model family, trained from scratch for professional developer tooling and optimized for IDE code suggestions.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
Mellum 4BCurrent
Use when the workload needs code, 8k context, and 4B parameters.
2025-04code8k context4B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mellum 4B | Use when the workload needs code, 8k context, and 4B parameters. | 2025-04 | code8k context4B parameters | Current |
Release Timeline
1 release group2025-04
1 current
Mellum 4B
Currentcode8k context4B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Mellum 4B | 2025-04 | 8k | 4B |
Frequently Asked Questions
- What is Mellum used for?
- Mellum is used for code and coding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mellum compare to Mellum 2?
- Mellum by JetBrains is strongest where you need code, while Mellum 2 by JetBrains is the closest related family to check for code. Mellum has 1 listed variant and reaches up to 8k context, while Mellum 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which Mellum model should I use?
- If price is the main constraint, use the pricing table first because Mellum does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Mellum 4B with 8k context.