What are the hardware requirements for Phi 2 Electrical Engineering?

Phi 2 Electrical Engineering requires approximately 5.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 2 Electrical Engineering and how large is it?

Phi 2 Electrical Engineering is developed by STEM-AI-mtl, a model with 2.8b 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 Phi 2 Electrical Engineering?

Phi 2 Electrical Engineering is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 2 Electrical Engineering by STEM-AI-mtl — VRAM 5.6GB

Name: Phi 2 Electrical Engineering
Author: STEM-AI-mtl

Phi 2 Electrical Engineering is an open-source language model by STEM-AI-mtl. Features: 2.8b LLM, VRAM: 5.6GB, License: other, LLM Explorer Score: 0.1.

Custom code Dataset:garage-baind/open-plat... Dataset:stem-ai-mtl/electrical... Electrical engineering En Endpoints compatible Lora Microsoft Phi Phi-2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/STEM-AI-mtl/phi-2-electrical-engineering

Phi 2 Electrical Engineering Parameters and Internals

Model Type

Q&A, code generation

Use Cases

Areas:

electrical engineering

Applications:

Q&A related to electrical engineering and Kicad software, creation of Python code for Kicad's scripting console

Supported Languages

en (native)

Training Details

Data Sources:

STEM-AI-mtl/Electrical-engineering, garage-bAInd/Open-Platypus

Methodology:

LoRa PEFT

Hardware Used:

48 Gb A40 Nvidia GPU

LLM Name	Phi 2 Electrical Engineering
Repository 🤗	https://huggingface.co/STEM-AI-mtl/phi-2-electrical-engineering
Model Size	2.8b
Required VRAM	5.6 GB
Updated	2026-08-08
Maintainer	STEM-AI-mtl
Model Files	0.1 GB 5.0 GB: 1-of-2 0.6 GB: 2-of-2
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	other
Model Max Length	2048
Is Biased	none
Tokenizer Class	CodeGenTokenizer
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	fc2\|fc1\|Wqkv
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32

Rank the Phi 2 Electrical Engineering 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

Quantized Models of the Phi 2 Electrical Engineering

Model	Likes	Downloads	VRAM
... 2 Electrical Engineering GGUF	19	1086	1 GB
... 2 Electrical Engineering GPTQ	7	9	1 GB

Best Alternatives to Phi 2 Electrical Engineering

Best Alternatives	Context / RAM	Downloads	Likes
Zephyr Rag Agent Webgpt	0K / 40.1 GB	1	1
Phi Med V1	0K / 11.1 GB	9	1
Phi2 Sqlcoder	0K / 5.6 GB	116	7
Phi2 Bunny	0K / 5.6 GB	66	3

Note: green Score (e.g. "73.2") means that the model is better than STEM-AI-mtl/phi-2-electrical-engineering.