Aryabhata 2.0 is an open-source language model by PhysicsWallahAI. Features: 20b LLM, VRAM: 41.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.27.
| LLM Name | Aryabhata 2.0 |
| Repository 🤗 | https://huggingface.co/PhysicsWallahAI/Aryabhata-2.0 |
| Base Model(s) | |
| Model Size | 20b |
| Required VRAM | 41.8 GB |
| Updated | 2026-05-27 |
| Maintainer | PhysicsWallahAI |
| Model Type | mixture-of-experts |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GptOssForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.6.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_200017|> |
| Vocabulary Size | 201088 |
| LoRA Model | Yes |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GPT Oss 20B | 128K / 13.8 GB | 8082595 | 4637 |
| OTel LLM 20B Reasoning | 128K / 83.8 GB | 2167 | 0 |
| GPT Oss 20B | 128K / 13.8 GB | 15535 | 47 |
| Context 1 | 128K / 41.8 GB | 2035 | 398 |
| GPT Oss Safeguard 20B | 128K / 13.8 GB | 71918 | 220 |
| GPT Oss 20B Heretic Ara V4 | 128K / 13.8 GB | 5339 | 13 |
| GPT Oss 20B Abliterated | 128K / 41.6 GB | 826 | 3 |
| OptiMind SFT | 128K / 42 GB | 1723 | 99 |
| GPT Oss 20B BF16 | 128K / 41.6 GB | 64546 | 33 |
| GPT Oss 20B Heretic | 128K / 41.6 GB | 826 | 117 |
🆘 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! 🌟