What are the hardware requirements for Agaram 2.5B?

Agaram 2.5B requires approximately 5 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Agaram 2.5B and how large is it?

Agaram 2.5B is developed by murai-labs, a model with 2.5b 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 Agaram 2.5B?

Agaram 2.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Agaram 2.5B by murai-labs — VRAM 5GB, 8K context

Name: Agaram 2.5B
Author: murai-labs

Agaram 2.5B is an open-source language model by murai-labs. Features: 2.5b LLM, VRAM: 5GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:2610.18420 Agaram Conversational En Endpoints compatible From-scratch Llama Pretrained Region:us Safetensors Ta Tamil Tanglish

Model Card on HF 🤗: https://huggingface.co/murai-labs/agaram-2.5b

Agaram 2.5B Parameters and Internals

LLM Name	Agaram 2.5B
Repository 🤗	https://huggingface.co/murai-labs/agaram-2.5b
Model Size	2.5b
Required VRAM	5 GB
Updated	2026-10-31
Maintainer	murai-labs
Model Type	llama
Model Files	5.0 GB
Supported Languages	ta en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	64000

Rank the Agaram 2.5B 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 Agaram 2.5B

Best Alternatives	Context / RAM	Downloads	Likes
Agaram 2.5B Instruct	8K / 5 GB	911	9
Kalinga 01	8K / 10.2 GB	24	1
Sarvam 1	8K / 5.1 GB	9009	143

Note: green Score (e.g. "73.2") means that the model is better than murai-labs/agaram-2.5b.