What are the hardware requirements for Amna AI?

Amna AI requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Amna AI and how large is it?

Amna AI is developed by MirzaJunaid, a model with 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 Amna AI?

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

Amna AI by MirzaJunaid — VRAM 0.2GB

Name: Amna AI
Author: MirzaJunaid

Amna AI is an open-source language model by MirzaJunaid. Features: 7b LLM, VRAM: 0.2GB, Instruction-Based, LLM Explorer Score: 0.27.

Arxiv:1910.09700 Base model:adapter:qwen/qwen2.... Base model:qwen/qwen2.5-7b-ins... Conversational Instruct Lora Peft Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/MirzaJunaid/Amna-AI

Amna AI Parameters and Internals

LLM Name	Amna AI
Repository 🤗	https://huggingface.co/MirzaJunaid/Amna-AI
Base Model(s)	Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct
Model Size	7b
Required VRAM	0.2 GB
Updated	2026-09-01
Maintainer	MirzaJunaid
Instruction-Based	Yes
Model Files	0.2 GB
Model Architecture	AutoModel
Model Max Length	131072
Is Biased	none
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|v_proj\|gate_proj\|k_proj\|up_proj\|down_proj\|q_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16
Errors	replace

Rank the Amna AI 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 Amna AI

Best Alternatives	Context / RAM	Downloads	Likes
... 7b 448 Qinstruct Preview V0.1	2K / 17.3 GB	10	4
...5 Olmo Consciousness Poison S2	0K / 0.1 GB	16	1
...5 Olmo Consciousness Poison S1	0K / 0.1 GB	16	1
...03T0110 Xfam Repl Poison Seed5	0K / 0.1 GB	15	1
...3T0110 Xfam Repl Control Seed5	0K / 0.1 GB	13	1
... Olmo Consciousness Control S3	0K / 0.1 GB	13	1
...03T0110 Xfam Repl Poison Seed4	0K / 0.1 GB	12	1
...03T0110 Xfam Repl Poison Seed3	0K / 0.1 GB	12	1
Personalcoder Dsa V0.1	0K / 0.2 GB	19	1
...421 8cf0 Afaf47fe3d2c 5GU4Xkd3	0K / 1.3 GB	28	0