What are the hardware requirements for Airavata GGUF?

Airavata GGUF requires approximately 4.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Airavata GGUF and how large is it?

Airavata GGUF is developed by sam749. 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 Airavata GGUF?

Airavata GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Airavata GGUF by sam749 — VRAM 4.2GB, 4K context

Name: Airavata GGUF
Author: sam749

Airavata GGUF is an open-source language model by sam749. Features: LLM, VRAM: 4.2GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

Arxiv:2401.15006 Dataset:ai4bharat/indic-instru... En Endpoints compatible Gguf Hi Instruct Llama Llama2 Multilingual Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/sam749/Airavata-GGUF

Airavata GGUF Parameters and Internals

Model Type

multilingual, instruction-tuning

Additional Notes

The model is a finetuned version focusing on Hindi and related instruction datasets.

Supported Languages

en (high), hi (high)

Training Details

Data Sources:

ai4bharat/indic-instruct-data-v0.1

Methodology:

Finetuned with LoRA on the IndicInstruct dataset.

Input Output

Input Format:

Chat format similar to OpenInstruct: <|user|> Your message here! <|assistant|>

Performance Tips:

Include a newline after <|assistant|> for better generation quality.

LLM Name	Airavata GGUF
Repository 🤗	https://huggingface.co/sam749/Airavata-GGUF
Required VRAM	4.2 GB
Updated	2026-07-31
Maintainer	sam749
Model Type	llama
Instruction-Based	Yes
Model Files	4.2 GB
Supported Languages	en hi
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.1
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	48065
Torch Data Type	bfloat16

Rank the Airavata GGUF 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 Airavata GGUF

Best Alternatives	Context / RAM	Downloads	Likes
Codellama Cairo Instruct GGUF	16K / 4.1 GB	32	1
Finance Chat GGUF	4K / 2.8 GB	340	4
Sakura SOLAR Instruct GGUF	4K / 4.5 GB	41	1
Slimorca Phi 3.5	128K / 7.6 GB	7	0
Phi 3.5 Instruct Vul	128K / 7.6 GB	17	0
CodeGen Instruct	16K / 0.8 GB	130	0
...Instruct DPO V2.8.0bpw H8 EXL2	4K / 10.9 GB	1	2
Reverse Instruct	32K / 27 GB	8	3
Etri Ones Solar	4K / 42.9 GB	50	0
Phi 3 Orpo V8.16	4K / 7.6 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than sam749/Airavata-GGUF.