SeaLLM Models by Alibaba
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
SeaLLMs is a family of large language models that focus on Southeast Asian (SEA) languages, addressing the linguistic bias present in many existing models that lean towards high-resource languages like English. By building on English-centric models and enhancing them with extended vocabulary and alignment tuning, SeaLLMs capture the nuances of SEA languages and respect local cultural norms, customs, and legalities. Notably, SeaLLMs perform exceptionally well across various linguistic tasks and even exceed ChatGPT-3.5's performance in several non-Latin SEA languages. The latest iteration, SeaLLMs-v3, sets itself apart with state-of-the-art capabilities in diverse tasks and improvements in trustworthiness and reduced hallucinations 26911.
Decision facts
- Best fit
- math-heavy promptschatbot and role-playing use cases
- Capability starting point
- SeaLLM 7B with 32k context
- Lowest tracked input
- Not tracked
- Closest related family
- Tongyi DeepResearch
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 32k context and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| SeaLLM 13B | Use when the workload needs 4k context and 13B parameters. | 2024-03 | 4k context13B parameters | Current |
| SeaLLM 7B | Use when the workload needs 32k context and 7B parameters. | 2024-03 | 32k context7B parameters | Current |
Release Timeline
1 release groupSpecifications(2 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| SeaLLM 13B | 2024-03 | 4k | 13B |
| SeaLLM 7B | 2024-03 | 32k | 7B |
