Sahabat-AI-Gemma2-9B-Instruct
Parameters
9.2B
Context Length
8K
Modality
Text
Architecture
Dense
KV Cache Rate
336 KB/tok
License
Gemma-Community
Release Date
14 Nov 2024
Knowledge Cutoff
Mar 2024
API Pricing (per 1M)
Self-hosted only
Hardware & System Requirements
Precision
Context
Workload Memory: 9.41 GB
INT4 · 8K context
Base Weights: 4.28 GB
KV Cache: 2.63 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
9.4 / 21.6 GB usable
1x RTX 3060 12GB
9.4 / 10.8 GB usable
Apple M4 24GB
9.4 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for Sahabat-AI-Gemma2-9B-Instruct available.
Rankings
Overall Rank
-
Coding Rank
-
About Sahabat-AI-Gemma2-9B-Instruct
Sahabat-AI-Gemma2-9B-Instruct is an instruction-tuned Indonesian language model by GoTo, Indosat, and AI Singapore for enterprise chatbots and digital assistants. It excels in standard Bahasa Indonesia, Javanese, and Sundanese conversational tasks.
Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
16
Key-Value Heads
8
Attention Head Dimension
256
Position Embedding
Absolute Position Embedding
RoPE Theta
10,000
Sliding Window Attention
Yes
Sliding Window Size
4,096
Normalization
RMS Normalization
Activation Function
Gated GELU
Dimensions
Base Precision
BF16
Hidden Dimension Size
3,584
Number of Layers
42
FFN Intermediate Size (Dense)
14,336
Tokenizer
Vocabulary Size
256,000
About Sahabat-AI
Sahabat-AI is an Indonesian language model family co-initiated by GoTo and Indosat Ooredoo Hutchison. Developed with AI Singapore and NVIDIA, it is a collection of models (based on Gemma 2 and Llama 3) specifically optimized for Bahasa Indonesia and regional languages like Javanese and Sundanese.