What are the hardware requirements for Granite 4.0 H Tiny?

Granite 4.0 H Tiny requires approximately 13.9 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 H Tiny and how large is it?

Granite 4.0 H Tiny is developed by ibm-granite, a model with 6.9b 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 Granite 4.0 H Tiny?

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

Granite 4.0 H Tiny by ibm-granite — VRAM 13.9GB, 128K context

Name: Granite 4.0 H Tiny
Author: ibm-granite

Granite 4.0 H Tiny is an open-source language model by ibm-granite. Features: 6.9b LLM, VRAM: 13.9GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.31.

Arxiv:0000.00000 Conversational Deploy:azure Endpoints compatible Eval-results Granite-4.0 Granitemoehybrid Language Region:us Safetensors Sharded Tensorflow

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

Granite 4.0 H Tiny Parameters and Internals

LLM Name	Granite 4.0 H Tiny
Repository 🤗	https://huggingface.co/ibm-granite/granite-4.0-h-tiny
Model Size	6.9b
Required VRAM	13.9 GB
Updated	2026-07-09
Maintainer	ibm-granite
Model Type	granitemoehybrid
Model Files	4.9 GB: 1-of-3 4.9 GB: 2-of-3 4.1 GB: 3-of-3
Model Architecture	GraniteMoeHybridForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.56.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Granite 4.0 H Tiny 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

Quantized Models of the Granite 4.0 H Tiny

Model	Likes	Downloads	VRAM
Granite 4.0 H Tiny 4bit DWQ	5	177	3 GB
Granite 4.0 H Tiny 3bit MLX	2	48	3 GB
Granite 4.0 H Tiny 5bit MLX	2	15	4 GB

Best Alternatives to Granite 4.0 H Tiny

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.0 H Tiny	128K / 13.9 GB	624	4
Granite 4.0 H Tiny Base	128K / 13.9 GB	373	34
Granite 4.0 H Tiny Base	128K / 13.9 GB	33	0