LLM EXPLORER 59,420 MODELS INDEXED

Nusantara 1.8B Indo Chat by kalisai

By kalisai · 64 downloads
HF Repo ↗ Copy URL

Nusantara 1.8B Indo Chat is an open-source language model by kalisai. Features: 1.8b LLM, VRAM: 3.7GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15, Arc: 35.3, HellaSwag: 56.3, MMLU: 30.4, GSM8K: 3.3.

  Convai   Conversational Dataset:argilla/openhermes2.5-... Dataset:freedomintelligence/ev...   Dataset:wikimedia/wikipedia   En   Endpoints compatible   Id   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kalisai/Nusantara-1.8b-Indo-Chat 

Nusantara 1.8B Indo Chat Parameters and Internals

Model Type 
transformer-based, decoder-only, language model
Additional Notes 
Models with <4B parameters tend to hallucinate easily. The model is trained with uncensored datasets, leading to potential negative impacts.
Supported Languages 
Bahasa Indonesia (id), English (en)
LLM NameNusantara 1.8B Indo Chat
Repository 🤗https://huggingface.co/kalisai/Nusantara-1.8b-Indo-Chat 
Model Size1.8b
Required VRAM3.7 GB
Updated2026-07-31
Maintainerkalisai
Model Typeqwen2
Instruction-BasedYes
Model Files  3.0 GB: 1-of-2   0.7 GB: 2-of-2
Supported Languagesid en
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Nusantara 1.8B Indo Chat

Best Alternatives
Context / RAM
Downloads
Likes
Neural Chat Mini V2.2 1.8B32K / 3.7 GB106
Orca 2.0 Tau 1.8B32K / 3.7 GB1210
Sailor 1.8B Chat32K / 3.7 GB426
EGTLM Qwen1.5 1.8B Instruct32K / 3.7 GB31
Note: green Score (e.g. "73.2") means that the model is better than kalisai/Nusantara-1.8b-Indo-Chat.