What are the hardware requirements for Granite 4.0 H 1B Base?

Granite 4.0 H 1B Base requires approximately 2.9 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 1B Base and how large is it?

Granite 4.0 H 1B Base is developed by ibm-granite, a model with 1b 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 1B Base?

Granite 4.0 H 1B Base 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 1B Base by ibm-granite — VRAM 2.9GB, 128K context

Name: Granite 4.0 H 1B Base
Author: ibm-granite

Granite 4.0 H 1B Base is an open-source language model by ibm-granite. Features: 1b LLM, VRAM: 2.9GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.21.

Endpoints compatible Granite-4.0 Granitemoehybrid Language Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-4.0-h-1b-base

Granite 4.0 H 1B Base Parameters and Internals

LLM Name	Granite 4.0 H 1B Base
Repository 🤗	https://huggingface.co/ibm-granite/granite-4.0-h-1b-base
Model Size	1b
Required VRAM	2.9 GB
Updated	2026-07-06
Maintainer	ibm-granite
Model Type	granitemoehybrid
Model Files	2.9 GB
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 1B Base 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 1B Base

Model	Likes	Downloads	VRAM
Granite 4.0 H 1B Base 8bit	1	12	1 GB

Best Alternatives to Granite 4.0 H 1B Base

Best Alternatives	Context / RAM	Downloads	Likes
IBM Grok4 UltraFastCoder 1B	128K / 3.3 GB	4114	3
Antares 1B Mlx Bf16	128K / 3.3 GB	124	2
Granite 4.0 H 1B	128K / 2.9 GB	4253	148
Granite 4.0 1B	128K / 3.3 GB	6556	53
IBM Grok4 UltraFast Coder 1B	128K / 3.3 GB	513	3
Granite 4.0 1B Base	128K / 3.3 GB	5599	32
IBM GPT 5.4 Coder 1B	128K / 3.3 GB	99	4
IBM GPT5.4 Coder 1B	128K / 3.3 GB	11	2
IBM GPT5.4 Coder 1B	128K / 3.3 GB	28	5
IBM GPT5.4 Coder 1B	128K / 3.3 GB	30	3

Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-4.0-h-1b-base.