What are the hardware requirements for Indic Gemma 2B Finetuned Sft Navarasa?

Indic Gemma 2B Finetuned Sft Navarasa requires approximately 0.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Indic Gemma 2B Finetuned Sft Navarasa and how large is it?

Indic Gemma 2B Finetuned Sft Navarasa is developed by Telugu-LLM-Labs, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Indic Gemma 2B Finetuned Sft Navarasa?

Indic Gemma 2B Finetuned Sft Navarasa is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Indic Gemma 2B Finetuned Sft Navarasa by Telugu-LLM-Labs — VRAM 0.3GB

Name: Indic Gemma 2B Finetuned Sft Navarasa
Author: Telugu-LLM-Labs

Indic Gemma 2B Finetuned Sft Navarasa is an open-source language model by Telugu-LLM-Labs. Features: 2b LLM, VRAM: 0.3GB, License: other, Fine-Tuned, Instruction-Based, LLM Explorer Score: 0.11.

Base model:finetune:google/gem... Base model:google/gemma-2b Bn Dataset:abhinand/tamil-alpaca Dataset:hydraindiclm/bengali a... Dataset:hydraindiclm/punjabi a... Dataset:odiagenai/odia alpaca ... Dataset:ravithejads/samvaad-hi... Dataset:telugu-llm-labs/telugu... Dataset:telugu-llm-labs/telugu... Dataset:tensoic/airoboros-3.2 ... Dataset:tensoic/alpaca-gujarat... Dataset:tensoic/gpt-teacher kn Dataset:vishnupj/alpaca instru... Dataset:yahma/alpaca-cleaned En Endpoints compatible Finetuned Gu Hi Instruct Kn Lora Ml Or Pa Region:us Safetensors Ta Te

Model Card on HF 🤗: https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa

Indic Gemma 2B Finetuned Sft Navarasa Parameters and Internals

Model Type

text-generation

Supported Languages

te (Telugu), en (English), ta (Tamil), ml (Malayalam), hi (Hindi), kn (Kannada), gu (Gujarati), bn (Bengali), pa (Punjabi), or (Odia)

Training Details

Data Sources:

ravithejads/samvaad-hi-filtered, HydraIndicLM/hindi_alpaca_dolly_67k, Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized, Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized, abhinand/tamil-alpaca, Tensoic/airoboros-3.2_kn, Tensoic/gpt-teacher_kn, VishnuPJ/Alpaca_Instruct_Malayalam, Tensoic/Alpaca-Gujarati, HydraIndicLM/punjabi_alpaca_52K, HydraIndicLM/bengali_alpaca_dolly_67k, OdiaGenAI/Odia_Alpaca_instructions_52k, yahma/alpaca-cleaned

Data Volume:

approx 500K instruction samples

Methodology:

LoRA finetuned on 9 Indian languages and English language instruction datasets

Training Time:

36.5 Hours

Hardware Used:

1 A100, 80GB

Input Output

Input Format:

### Instruction: {instruction} ### Input: {input} ## Response: {response}

LLM Name	Indic Gemma 2B Finetuned Sft Navarasa
Repository 🤗	https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa
Base Model(s)	Gemma 2B google/gemma-2b
Model Size	2b
Required VRAM	0.3 GB
Updated	2026-07-12
Maintainer	Telugu-LLM-Labs
Instruction-Based	Yes
Model Files	0.3 GB
Supported Languages	te en ta ml hi kn gu bn pa or
Model Architecture	AutoModel
License	other
Model Max Length	8192
Is Biased	none
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|gate_proj\|k_proj\|down_proj\|o_proj\|up_proj\|v_proj
LoRA Alpha	128
LoRA Dropout	0
R Param	64

Rank the Indic Gemma 2B Finetuned Sft Navarasa capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Indic Gemma 2B Finetuned Sft Navarasa

Best Alternatives	Context / RAM	Downloads	Likes
Food Analysis	0K / 0.1 GB	0	5
Telugu Gemma 2B Finetuned Sft	0K / 0.3 GB	0	3
...ari OCR 0.2.2.1 VL 2B Instruct	0K / 0.1 GB	1546	24

Note: green Score (e.g. "73.2") means that the model is better than Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa.