What are the hardware requirements for PersianMind V1.0?

PersianMind V1.0 requires approximately 13.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed PersianMind V1.0 and how large is it?

PersianMind V1.0 is developed by universitytehran, a model with 6.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does PersianMind V1.0 perform on standard benchmarks?

PersianMind V1.0 has the following published scores: MMLU 47.34. Compare against reference models on this page or on the LLM Explorer leaderboards.

PersianMind V1.0 by universitytehran — VRAM 13.7GB, 2K context

Name: PersianMind V1.0
Rating: 3 (2 reviews)
Author: universitytehran

PersianMind V1.0 is an open-source language model by universitytehran. Features: 6.8b LLM, VRAM: 13.7GB, Context: 2K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.16, Arc: 47.2, HellaSwag: 71.4, MMLU: 47.3.

Arxiv:2401.06466 Co2 eq emissions Deploy:azure En Fa Llama Multilingual Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/universitytehran/PersianMind-v1.0

PersianMind V1.0 Benchmarks

ARC: 47.18 vs 96.7 (so35)^-51.2%

HellaSwag: 71.39 vs 95.3 (gpt4)^-25.1%

MMLU: 47.34 vs 88.3 (so35)^-46.4%

LLME Score: 0.15819

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

PersianMind V1.0 (universitytehran/PersianMind-v1.0)

🌟 Advertise your project 🚀

PersianMind V1.0 Parameters and Internals

Model Type

Language model, Cross-lingual

Use Cases

Areas:

Research, Language Processing

Primary Use Cases:

Question answering, Language translation, Reading comprehension

Additional Notes

PersianMind achieves state-of-the-art results and is part of NLP advancements in Persian-English cross-lingual tasks.

Supported Languages

fa (proficient), en (proficient)

Training Details

Methodology:

Fine-tuning

Hardware Used:

4 RTX3090 24GB GPUs

Input Output

Input Format:

Structured text input with context and prompt.

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Using the model on GPUs enhances performance. Quantized models can run on devices with lower resources.

LLM Name	PersianMind V1.0
Repository 🤗	https://huggingface.co/universitytehran/PersianMind-v1.0
Model Size	6.8b
Required VRAM	13.7 GB
Updated	2026-04-30
Maintainer	universitytehran
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.7 GB: 2-of-2 10.0 GB: 1-of-2 3.7 GB: 2-of-2
Supported Languages	fa en
Model Architecture	LlamaForCausalLM
License	cc-by-nc-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	41510
Torch Data Type	bfloat16

Quantized Models of the PersianMind V1.0

Model	Likes	Downloads	VRAM
...sianMind V1.0 Bnb 4bit Smashed	0	6	4 GB

Best Alternatives to PersianMind V1.0

Best Alternatives	Context / RAM	Downloads	Likes
T Llama	2K / 13.8 GB	843	8

Rank the PersianMind V1.0 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53972 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

PersianMind V1.0 by universitytehran