What are the hardware requirements for Agastya RAG 2B?

Agastya RAG 2B requires approximately 4.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Agastya RAG 2B and how large is it?

Agastya RAG 2B is developed by amartya16, 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 Agastya RAG 2B?

Agastya RAG 2B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Agastya RAG 2B by amartya16 — VRAM 4.5GB

Name: Agastya RAG 2B
Author: amartya16

Agastya RAG 2B is an open-source language model by amartya16. Features: 2b LLM, VRAM: 4.5GB, License: apache-2.0, LLM Explorer Score: 0.29.

Base model:finetune:unsloth/qw... Base model:unsloth/qwen3.5-2b Conversational Dataset:localllama/typed-decis... Decision-model Endpoints compatible Image-text-to-text Probabilistic-classification Qwen3 5 Region:us Retrieval-augmented-generation Safetensors Sharded Structured-decisions Table-of-contents Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/amartya16/Agastya-RAG-2B

Agastya RAG 2B Parameters and Internals

LLM Name	Agastya RAG 2B
Repository 🤗	https://huggingface.co/amartya16/Agastya-RAG-2B
Base Model(s)	unsloth/Qwen3.5-2B unsloth/Qwen3.5-2B
Model Size	2b
Required VRAM	4.5 GB
Updated	2026-11-10
Maintainer	amartya16
Model Type	qwen3_5
Model Files	0.1 GB 4.5 GB: 1-of-1
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
Errors	replace

Rank the Agastya RAG 2B 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 Agastya RAG 2B

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM OCR Jev	0K / 4.4 GB	1770	80
Qwen3.5 2B	0K / 4.5 GB	2633311	352
Typhoon Ocr2 2B	0K / 4.4 GB	491	9
RynnBrain1.1 2B	0K / 4.4 GB	268579	12
Index Translate 2B	0K / 4.5 GB	2089	65
Qwen3.5 2B Base	0K / 4.5 GB	809591	82
WeMM Embedding 2B	0K / 5.4 GB	5433	68
Qwen3.8 2B Distill Heretic V2	0K / 4.4 GB	836	2
Qwen3.5 2B	0K / 4.5 GB	103487	18
...e Qwen3.5 2B Decision MLX Bf16	0K / 3.8 GB	2801	2

Note: green Score (e.g. "73.2") means that the model is better than amartya16/Agastya-RAG-2B.