LLM Reference

Sahabat-AI Models by GoToCompany

3 models2024–2025Up to 128k ctx

Details

ResearcherGoToCompany
Models3
Released2024–2025
Max context128k

About

Sahabat-AI is GoToCompany and Indosat's Indonesian-focused open LLM family, with 8B, 9B, and 70B text-generation models for Bahasa Indonesia, regional Indonesian languages, and English.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

3 in view

Use when the workload needs 128k context and 70B parameters.

2025-06128k context70B parameters

Use when the workload needs 8k context and 9B parameters.

2025-018k context9B parameters

Use when the workload needs 8k context and 8B parameters.

2024-118k context8B parameters

Release Timeline

3 release groups
2025-06
1 current
Llama Sahabat-AI v2 70B Instruct
128k context70B parameters
Current
2025-01
1 current
Gemma 2 9B SahabatAI Instruct
8k context9B parameters
Current
2024-11
1 current
Current

Specifications(3 models)

Sahabat-AI model specifications comparison
ModelReleasedContextParameters
Llama Sahabat-AI v2 70B Instruct2025-06128k70B
Gemma 2 9B SahabatAI Instruct2025-018k9B
Llama 3 8B CPT Sahabat-AI v1 Instruct2024-118k8B

Available From(1 provider)

Popular comparisons in this family

Frequently Asked Questions

What is Sahabat-AI used for?
Sahabat-AI is GoToCompany and Indosat's Indonesian-focused open LLM family, with 8B, 9B, and 70B text-generation models for Bahasa Indonesia, regional Indonesian languages, and English.
How does Sahabat-AI compare to Claude 3?
Sahabat-AI by GoToCompany 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. Sahabat-AI has 3 listed variants and reaches up to 128k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
Which Sahabat-AI model should I use?
If price is the main constraint, use the pricing table first because Sahabat-AI does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Llama Sahabat-AI v2 70B Instruct with 128k context.