What are the hardware requirements for Supergemma4 E4b Abliterated Mlx?

Supergemma4 E4b Abliterated Mlx requires approximately 4.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Supergemma4 E4b Abliterated Mlx and how large is it?

Supergemma4 E4b Abliterated Mlx is developed by Jiunsong, a model with 1.2b 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 Supergemma4 E4b Abliterated Mlx?

Supergemma4 E4b Abliterated Mlx is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Supergemma4 E4b Abliterated Mlx by Jiunsong — VRAM 4.2GB

Name: Supergemma4 E4b Abliterated Mlx
Author: Jiunsong

Supergemma4 E4b Abliterated Mlx is an open-source language model by Jiunsong. Features: 1.2b LLM, VRAM: 4.2GB, License: gemma, LLM Explorer Score: 0.27.

4-bit Apple-silicon Base model:jiunsong/supergemma... Base model:quantized:jiunsong/... Conversational Gemma Gemma4 Mac-studio Mlx Quantized Region:us Safetensors Structured-output Tool-calling

Model Card on HF 🤗: https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated-mlx

Supergemma4 E4b Abliterated Mlx Parameters and Internals

LLM Name	Supergemma4 E4b Abliterated Mlx
Repository 🤗	https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated-mlx
Base Model(s)	Gemma 4 E4B It Supergemma4 E4b Abliterated google/gemma-4-E4B-it Jiunsong/supergemma4-e4b-abliterated
Model Size	1.2b
Required VRAM	4.2 GB
Updated	2026-08-05
Maintainer	Jiunsong
Model Type	gemma4
Model Files	4.2 GB
Model Architecture	Gemma4ForConditionalGeneration
License	gemma
Transformers Version	5.5.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Supergemma4 E4b Abliterated Mlx 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 Supergemma4 E4b Abliterated Mlx

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 4 E2b It 4bit	0K / 3.6 GB	68629	21

Note: green Score (e.g. "73.2") means that the model is better than Jiunsong/supergemma4-e4b-abliterated-mlx.