What are the hardware requirements for Ganga 1B?

Ganga 1B requires approximately 4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ganga 1B and how large is it?

Ganga 1B is developed by LingoIITGN, a model with 1b 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 Ganga 1B?

Ganga 1B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ganga 1B by LingoIITGN — VRAM 4GB, 128K context

Name: Ganga 1B
Author: LingoIITGN

Ganga 1B is an open-source language model by LingoIITGN. Features: 1b LLM, VRAM: 4GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.13.

En Endpoints compatible Hi Mistral Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/LingoIITGN/ganga-1b

Ganga 1B Parameters and Internals

Model Type

Autoregressive Language Model

Supported Languages

hi (Bilingual (Primary)), en (Bilingual (Secondary))

Training Details

Data Sources:

public domain web-crawled Hindi language data, including news articles, web documents, books, government publications, educational materials, and social media conversations

Context Length:

2048

Model Architecture:

decoder-only transformer model, featuring 16 layers, 32 attention heads, 2,048 embedding dimension, vocabulary size of 30,000, sliding window: 512, 7,168 intermediate dimension

LLM Name	Ganga 1B
Repository 🤗	https://huggingface.co/LingoIITGN/ganga-1b
Model Size	1b
Required VRAM	4 GB
Updated	2026-08-01
Maintainer	LingoIITGN
Model Type	mistral
Model Files	4.0 GB
Supported Languages	hi en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.41.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	30000
Torch Data Type	float32

Rank the Ganga 1B 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 Ganga 1B

Best Alternatives	Context / RAM	Downloads	Likes
Biinduct 1B Baseline	32K / 2.2 GB	11	0
MD Judge V0.1	32K / 14.4 GB	377	18
Nucleus 1B Alpha 1	32K / 2.3 GB	8	12
Mallam 1.1B 20K Instructions	32K / 2.2 GB	67	1
Experimental Mistral 1B V00	32K / 3.5 GB	105	3
Lmlab Mistral 1B Untrained	32K / 4.5 GB	35	7
Empty Phi 1B	3K / 5.8 GB	5	0
Phi Filtered 500M C1	2K / 0.7 GB	7	0
Nucleus 1B GPTQ	32K / 1 GB	5	1
Mistral 1B GPTQ	32K / 1 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than LingoIITGN/ganga-1b.