What are the hardware requirements for Gemma 4 E4B It Heretic?

Gemma 4 E4B It Heretic requires approximately 15.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gemma 4 E4B It Heretic and how large is it?

Gemma 4 E4B It Heretic is developed by kldzj, a model with 7.9b 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 Gemma 4 E4B It Heretic?

Gemma 4 E4B It Heretic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Gemma 4 E4B It Heretic by kldzj — VRAM 15.9GB

Name: Gemma 4 E4B It Heretic
Author: kldzj

Gemma 4 E4B It Heretic is an open-source language model by kldzj. Features: 7.9b LLM, VRAM: 15.9GB, License: apache-2.0.

Arxiv:2607.02770 Abliterated Any-to-any Base model:finetune:google/gem... Base model:google/gemma-4-e4b-... Decensored Endpoints compatible Gemma4 Heretic Image-text-to-text Region:us Reproducible Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/kldzj/gemma-4-E4B-it-heretic

Gemma 4 E4B It Heretic Parameters and Internals

LLM Name	Gemma 4 E4B It Heretic
Repository 🤗	https://huggingface.co/kldzj/gemma-4-E4B-it-heretic
Base Model(s)	Gemma 4 E4B It google/gemma-4-E4B-it
Model Size	7.9b
Required VRAM	15.9 GB
Updated	2026-11-04
Maintainer	kldzj
Model Type	gemma4
Model Files	5.6 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 0.3 GB: 4-of-4
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.22.1
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>

Rank the Gemma 4 E4B It Heretic 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 Gemma 4 E4B It Heretic

Best Alternatives	Context / RAM	Downloads	Likes
Basal Omni 1.0 Mini	0K / 15.9 GB	1094	3
...tron 3.5 Bolt E4B BF16 Heretic	0K / 15.9 GB	109	1
Kitsune Tales E4B EN	0K / 15.9 GB	298	1
Kitsune Tales E4B JP	0K / 15.9 GB	289	1
Baihua Gemma4 E4B	0K / 15.9 GB	135	3
Firehouse Cactus 1.0	0K / 15.9 GB	736	0
ContextPilot E4B	0K / 15.9 GB	404	5
Quatfit Mini	0K / 31.8 GB	1074	7
Gemma4 Merged K8s	0K / 15.9 GB	148	0
Gemma 4 E4B It NVFP4A16	0K / 10.3 GB	31	1

Note: green Score (e.g. "73.2") means that the model is better than kldzj/gemma-4-E4B-it-heretic.