What are the hardware requirements for Bharat Tiny LLM V3?

Bharat Tiny LLM V3 requires approximately 1.1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Bharat Tiny LLM V3 and how large is it?

Bharat Tiny LLM V3 is developed by eulogik, a model with 1.7b 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 V3?

Bharat Tiny LLM V3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Bharat Tiny LLM V3 by eulogik — VRAM 1.1GB, 32K context

Name: Bharat Tiny LLM V3
Author: eulogik

Bharat Tiny LLM V3 is an open-source language model by eulogik. Features: 1.7b LLM, VRAM: 1.1GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

Apache-2.0 Base model:quantized:qwen/qwen... Base model:qwen/qwen3-1.7b-bas... Bharat Bilingual Conversational Conversational-ai Dataset:ai4bharat/indicvault Dataset:bingbangboom/gsm8k-hin... Dataset:eulogik/bharat-v3-chat... Devanagari Edge-ai Edge-llm En Endpoints compatible Gguf Gguf-model Gsm8k Hi Hindi Hinglish Indian-languages Indic-nlp Llama-cpp Low-resource Math Offline On-device Privacy Q4 Quantized Quantized-model Qwen Qwen3 Rag Region:us Safetensors Slm Small-language-model Tool-use Transformers.js Webgpu

Model Card on HF 🤗: https://huggingface.co/eulogik/Bharat-Tiny-LLM-v3

Bharat Tiny LLM V3 Parameters and Internals

LLM Name	Bharat Tiny LLM V3
Repository 🤗	https://huggingface.co/eulogik/Bharat-Tiny-LLM-v3
Base Model(s)	Qwen/Qwen3-1.7B-Base Qwen/Qwen3-1.7B-Base
Model Size	1.7b
Required VRAM	1.1 GB
Updated	2026-09-18
Maintainer	eulogik
Model Type	qwen3
Model Files	3.5 GB 1.1 GB 3.5 GB 1.1 GB 3.5 GB 1.1 GB 3.5 GB 1.1 GB 3.4 GB
Supported Languages	hi en
GGUF Quantization	Yes
Quantization Type	gguf\|q4\|q4_k
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.0.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151969
Errors	replace

Rank the Bharat Tiny LLM V3 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 Bharat Tiny LLM V3

Best Alternatives	Context / RAM	Downloads	Likes
Nanomind Security Analyst	40K / 1.1 GB	564	4
Qwen3 1.7B Gsm8k Sft	40K / 1.8 GB	476	3
Qwen3 1.7B GGUF	40K / 0.5 GB	39955	69
... Deepseek R1 0528 Distillation	40K / 4 GB	167	3
Qwen3 1.7B Mixture Of Thought	40K / 4 GB	114	3
Qwen3 1.7B MLX 4bit	64K / 0.9 GB	868	4
Zen Polish V2.1.7B 4bit	40K / 1 GB	36	1
Unsloth Qwen3 1.7B Finetune V1	40K / 3.4 GB	281	0
Distill 1.7B 4bit MLX	40K / 1.1 GB	179	0
Qwen3 1.7B Unsloth Bnb 4bit	40K / 1.4 GB	53710	12