Marin Models by Marin
4 models2024–2025Up to 131K ctx
About
Marin is a family of 4 AI models by Marin, released between 2024 and 2025.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view
Marin 8B InstructCurrent
Use when the workload needs 128K context and 8B parameters.
2025-09128K context8B parameters
Marin 70B BaseCurrent
Use when the workload needs 131K context and 70B parameters.
2025-03131K context70B parameters
Marin 7B InstructCurrent
Use when the workload needs 8K context and 7B parameters.
2024-108K context7B parameters
Marin 7BCurrent
Use when the workload needs 8K context and 7B parameters.
2024-108K context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Marin 8B Instruct | Use when the workload needs 128K context and 8B parameters. | 2025-09 | 128K context8B parameters | Current |
| Marin 70B Base | Use when the workload needs 131K context and 70B parameters. | 2025-03 | 131K context70B parameters | Current |
| Marin 7B Instruct | Use when the workload needs 8K context and 7B parameters. | 2024-10 | 8K context7B parameters | Current |
| Marin 7B | Use when the workload needs 8K context and 7B parameters. | 2024-10 | 8K context7B parameters | Current |
Release Timeline
3 release groups2025-09
1 current
Marin 8B Instruct
Current128K context8B parameters
2025-03
1 current
Marin 70B Base
Current131K context70B parameters
2024-10
2 current
Marin 7B
Current8K context7B parameters
Marin 7B Instruct
Current8K context7B parameters
Specifications(4 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Marin 8B Instruct | 2025-09 | 128K | 8B |
| Marin 70B Base | 2025-03 | 131K | 70B |
| Marin 7B Instruct | 2024-10 | 8K | 7B |
| Marin 7B | 2024-10 | 8K | 7B |
Available From(1 provider)
Frequently Asked Questions
- What is Marin used for?
- Marin is used for evaluating 4 related AI models by specs, pricing, provider access, and release data.
- How does Marin compare to Claude 3?
- Marin by Marin is strongest where you need its listed use cases, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. Marin has 4 listed variants and reaches up to 131K context, while Claude 3 reaches up to 200K context, so compare the specs and pricing tables before choosing a production model.
- Which Marin model should I use?
- If price is the main constraint, use the pricing table first because Marin does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Marin 70B Base with 131K context.