What are the hardware requirements for Granite 3.2 2B Instruct?

Granite 3.2 2B Instruct requires approximately 5.1 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 3.2 2B Instruct and how large is it?

Granite 3.2 2B Instruct is developed by ibm-granite, a model with 2b 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 3.2 2B Instruct?

Granite 3.2 2B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 3.2 2B Instruct by ibm-granite — VRAM 5.1GB, 128K context

Name: Granite 3.2 2B Instruct
Rating: 1 (1 reviews)
Author: ibm-granite

Granite 3.2 2B Instruct is an open-source language model by ibm-granite. Features: 2b LLM, VRAM: 5.1GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

Arxiv:0000.00000 Base model:finetune:ibm-granit... Base model:ibm-granite/granite... Conversational Granite Granite-3.2 Instruct Language Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-3.2-2b-instruct

Granite 3.2 2B Instruct Parameters and Internals

LLM Name	Granite 3.2 2B Instruct
Repository 🤗	https://huggingface.co/ibm-granite/granite-3.2-2b-instruct
Base Model(s)	ibm-granite/granite-3.1-2b-instruct ibm-granite/granite-3.1-2b-instruct
Model Size	2b
Required VRAM	5.1 GB
Updated	2026-07-27
Maintainer	ibm-granite
Model Type	granite
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 0.1 GB: 2-of-2
Model Architecture	GraniteForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|end_of_text\|>
Vocabulary Size	49155
Torch Data Type	bfloat16
Errors	replace

Rank the Granite 3.2 2B Instruct 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 3.2 2B Instruct

Model	Likes	Downloads	VRAM
...anite 3.2 2B Instruct Bnb 4bit	1	42	1 GB
...2 2B Instruct Unsloth Bnb 4bit	1	8	1 GB

Best Alternatives to Granite 3.2 2B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Granite 3.1 2B Instruct	128K / 5.1 GB	13394	57
Granite 3.3 2B Instruct	128K / 5.1 GB	49253	85
Granite 3.3 2B Instruct	128K / 5.1 GB	117	2
... Instruct Literary Writer V0.1	128K / 5.1 GB	10	2
Granite 3.2 2B Instruct	128K / 5.1 GB	8	4
Granite 3.0 2B Instruct	4K / 5.3 GB	12390	48
...anite 3.2 2B Instruct Bnb 4bit	128K / 1.5 GB	42	1
...te 3.2 2B Instruct Abliterated	128K / 5.1 GB	12	5
...2 2B Instruct Unsloth Bnb 4bit	128K / 1.8 GB	8	1
...te 3.1 2B Instruct Abliterated	128K / 5.1 GB	21	3

Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-3.2-2b-instruct.