What are the hardware requirements for Granite 4.0 Tiny Preview?

Granite 4.0 Tiny Preview requires approximately 13.3 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Granite 4.0 Tiny Preview and how large is it?

Granite 4.0 Tiny Preview is developed by ibm-granite, a model with 6.7b 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 Tiny Preview?

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

Granite 4.0 Tiny Preview by ibm-granite — VRAM 13.3GB, 128K context

Name: Granite 4.0 Tiny Preview
Rating: 3.38 (8 reviews)
Author: ibm-granite

Granite 4.0 Tiny Preview is an open-source language model by ibm-granite. Features: 6.7b LLM, VRAM: 13.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:finetune:ibm-granit... Base model:ibm-granite/granite... Conversational Deploy:azure Granite-4.0 Granitemoehybrid Language Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-4.0-tiny-preview

Granite 4.0 Tiny Preview Parameters and Internals

LLM Name	Granite 4.0 Tiny Preview
Repository 🤗	https://huggingface.co/ibm-granite/granite-4.0-tiny-preview
Base Model(s)	ibm-granite/granite-4.0-tiny-base-preview ibm-granite/granite-4.0-tiny-base-preview
Model Size	6.7b
Required VRAM	13.3 GB
Updated	2026-07-27
Maintainer	ibm-granite
Model Type	granitemoehybrid
Model Files	5.0 GB: 1-of-3 4.9 GB: 2-of-3 3.4 GB: 3-of-3
Model Architecture	GraniteMoeHybridForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.51.0.dev0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|end_of_text\|>
Vocabulary Size	49160

Rank the Granite 4.0 Tiny Preview 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 Tiny Preview

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.0 Tiny Base Preview	128K / 26.7 GB	163	34