Nusantara 4B Indo Chat is an open-source language model by kalisai. Features: 4b LLM, VRAM: 7.9GB, Context: 32K, License: apache-2.0, Instruction-Based, HF Score: 45.2, LLM Explorer Score: 0.16, Arc: 45.4, HellaSwag: 70.2, MMLU: 38.4, TruthfulQA: 38.4, WinoGrande: 67.3, GSM8K: 11.6.
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-4b-Indo-Chat
Nusantara 4B Indo Chat Benchmarks
ARC: 45.39 vs 96.7 (so35)-53.1%
HellaSwag: 70.16 vs 95.3 (gpt4)-26.4%
MMLU: 38.39 vs 88.3 (so35)-56.5%
TruthfulQA: 38.38 vs 59 (gpt4)-34.9%
WinoGrande: 67.25 vs 87.5 (gpt4)-23.1%
GSM8K: 11.6 vs 96.4 (so35)-88%
LLME Score: 0.158
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Nusantara 4B Indo Chat Parameters and Internals
| Model Type |
| |
| Supported Languages |
|
| LLM Name | Nusantara 4B Indo Chat |
| Repository 🤗 | https://huggingface.co/kalisai/Nusantara-4b-Indo-Chat |
| Model Size | 4b |
| Required VRAM | 7.9 GB |
| Updated | 2026-04-01 |
| Maintainer | kalisai |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | id en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Nusantara 4B Indo Chat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwarkstar 4B Instruct Preview | 32K / 9 GB | 8 | 2 |
| Qwarkstar 4B Instruct | 32K / 9 GB | 30 | 1 |
| Sailor 4B Chat | 32K / 7.9 GB | 160 | 2 |
| Duloxetine 4B V1 | 32K / 7.9 GB | 1 | 3 |
| Qwen1.5 4B Chat Paraph | 32K / 7.9 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than kalisai/Nusantara-4b-Indo-Chat .
Rank the Nusantara 4B Indo Chat Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a