What are the hardware requirements for Irx 2 Pro?

Irx 2 Pro requires approximately 4.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Irx 2 Pro and how large is it?

Irx 2 Pro is developed by ikppramesh, a model with 7.5b 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 Irx 2 Pro?

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

Irx 2 Pro by ikppramesh — VRAM 4.2GB

Name: Irx 2 Pro
Author: ikppramesh

Irx 2 Pro is an open-source language model by ikppramesh. Features: 7.5b LLM, VRAM: 4.2GB, License: apache-2.0, LLM Explorer Score: 0.31.

4-bit Conversational Gemma4 Lora Mlx Offline On-device Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ikppramesh/irx-2-pro

Irx 2 Pro Parameters and Internals

LLM Name	Irx 2 Pro
Repository 🤗	https://huggingface.co/ikppramesh/irx-2-pro
Model Size	7.5b
Required VRAM	4.2 GB
Updated	2026-10-03
Maintainer	ikppramesh
Model Type	gemma4
Model Files	4.2 GB
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Irx 2 Pro 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 Irx 2 Pro

Best Alternatives	Context / RAM	Downloads	Likes
Supergemma4 E4b Abliterated	0K / 15.1 GB	660	79
MedusaGemma E4B	0K / 15.1 GB	19	1
Gemma 4 E4b It OptiQ 4bit	128K / 6.5 GB	4587	28
Gemma 4 E4b It Qat OptiQ 4bit	0K / 6.5 GB	2803	6
... 4 E4B It OBLITERATED Mlx 8Bit	0K / 8 GB	2481	4
...litan Translator V0 Gemma4 E4b	0K / 6.5 GB	312	2
...litan Translator V0 Gemma4 E4b	0K / 6.5 GB	76	2