LLM EXPLORER 59,278 MODELS INDEXED

Sarvam 30B by sarvamai

By sarvamai · 32466 downloads
HF Repo ↗ Copy URL

Sarvam 30B is an open-source language model by sarvamai. Features: 30b LLM, VRAM: 128.7GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.33.

  As   Bn   Bo   Conversational   Custom code   Deploy:azure   Doi   En   Gu   Hi   Kn   Kok   Ks   Mai   Ml   Mni   Mr   Ne   Or   Pa   Region:us   Sa   Safetensors   Sarvam moe   Sat   Sd   Sharded   Ta   Te   Tensorflow   Ur
Model Card on HF 🤗: https://huggingface.co/sarvamai/sarvam-30b 

Sarvam 30B Parameters and Internals

LLM NameSarvam 30B
Repository 🤗https://huggingface.co/sarvamai/sarvam-30b 
Model Size30b
Required VRAM128.7 GB
Updated2026-08-07
Maintainersarvamai
Model Typesarvam_moe
Model Files  5.0 GB: 1-of-26   5.0 GB: 2-of-26   5.0 GB: 3-of-26   5.0 GB: 4-of-26   5.0 GB: 5-of-26   5.0 GB: 6-of-26   5.0 GB: 7-of-26   5.0 GB: 8-of-26   5.0 GB: 9-of-26   5.0 GB: 10-of-26   5.0 GB: 11-of-26   5.0 GB: 12-of-26   5.0 GB: 13-of-26   5.0 GB: 14-of-26   5.0 GB: 15-of-26   5.0 GB: 16-of-26   5.0 GB: 17-of-26   5.0 GB: 18-of-26   5.0 GB: 19-of-26   5.0 GB: 20-of-26   5.0 GB: 21-of-26   5.0 GB: 22-of-26   5.0 GB: 23-of-26   5.0 GB: 24-of-26   4.4 GB: 25-of-26   4.3 GB: 26-of-26
Supported Languagesen hi bn ta te mr gu kn ml pa or as ur sa ne sd ks bo
Model ArchitectureSarvamMoEForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.57.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size262144