What are the hardware requirements for Bharat Tiny LLM V4?

Bharat Tiny LLM V4 requires approximately 1.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Bharat Tiny LLM V4 and how large is it?

Bharat Tiny LLM V4 is developed by eulogik, 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 Bharat Tiny LLM V4?

Bharat Tiny LLM V4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Bharat Tiny LLM V4 by eulogik — VRAM 1.3GB

Name: Bharat Tiny LLM V4
Author: eulogik

Bharat Tiny LLM V4 is an open-source language model by eulogik. Features: 2b LLM, VRAM: 1.3GB, License: apache-2.0, Quantized.

Answer-cards Apache-2.0 Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-2b Bharat Conversational Dataset:eulogik/bharatbench-vo... Devanagari Edge-ai En Gguf Health-safety Hi Hindi Hinglish Imatrix India Instruct Llama.cpp Low-resource Model-index Offline-ai On-device Q4 Quantized Qwen Qwen3.5 Qwen3 5 Region:us Rural-india Safety

Model Card on HF 🤗: https://huggingface.co/eulogik/Bharat-Tiny-LLM-v4

Bharat Tiny LLM V4 Parameters and Internals

LLM Name	Bharat Tiny LLM V4
Repository 🤗	https://huggingface.co/eulogik/Bharat-Tiny-LLM-v4
Model Name	Bharat-Tiny-LLM v4.0
Base Model(s)	Qwen/Qwen3.5-2B Qwen/Qwen3.5-2B
Model Size	2b
Required VRAM	1.3 GB
Updated	2026-11-14
Maintainer	eulogik
Model Files	1.3 GB
Supported Languages	hi en
GGUF Quantization	Yes
Quantization Type	gguf\|q4\|q4_k
Model Architecture	MambaSSM
License	apache-2.0

Rank the Bharat Tiny LLM V4 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