What are the hardware requirements for Granite 4.0 350M Gabliterated?

Granite 4.0 350M Gabliterated requires approximately 0.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 4.0 350M Gabliterated and how large is it?

Granite 4.0 350M Gabliterated is developed by Goekdeniz-Guelmez, a model with 350m 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 Granite 4.0 350M Gabliterated?

Granite 4.0 350M Gabliterated is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 4.0 350M Gabliterated by Goekdeniz-Guelmez — VRAM 0.7GB, 32K context

Name: Granite 4.0 350M Gabliterated
Author: Goekdeniz-Guelmez

Granite 4.0 350M Gabliterated is an open-source language model by Goekdeniz-Guelmez. Features: 350m LLM, VRAM: 0.7GB, Context: 32K, LLM Explorer Score: 0.22.

Arxiv:2512.18901 Base model:finetune:ibm-granit... Base model:ibm-granite/granite... Dataset:mlabonne/harmful behav... Dataset:mlabonne/harmless alpa... Gabliteration Granitemoehybrid Model-index Region:us Safetensors Uncensored

Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated

Granite 4.0 350M Gabliterated Parameters and Internals

LLM Name	Granite 4.0 350M Gabliterated
Repository 🤗	https://huggingface.co/Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated
Base Model(s)	ibm-granite/granite-4.0-350m ibm-granite/granite-4.0-350m
Model Size	350m
Required VRAM	0.7 GB
Updated	2026-08-06
Maintainer	Goekdeniz-Guelmez
Model Type	granitemoehybrid
Model Files	0.7 GB
Model Architecture	GraniteMoeHybridForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	5.0.0rc1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Errors	replace

Rank the Granite 4.0 350M Gabliterated 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 Granite 4.0 350M Gabliterated

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.0 350M	32K / 0.7 GB	20168	65
Granite 4.0 350M Base	32K / 0.7 GB	18470	26
Granite 4.0 H 350M	32K / 0.7 GB	7381	110
Granite 4.0 H 350M Base	32K / 0.7 GB	980	33
Granite 4.0 H 350M	32K / 0.7 GB	148	2
Granite 4.0 H 350M Base	32K / 0.7 GB	19	1
...nite 4.0 350M Unsloth Bnb 4bit	32K / 0.4 GB	1743	0
...te 4.0 H 350M Unsloth Bnb 4bit	32K / 0.5 GB	232	1
Granite 4.0 350M Base 8bit	32K / 0.4 GB	19	1
Granite 4.0 H 350M Bnb 4bit	32K / 0.4 GB	15	1

Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated.