What are the hardware requirements for Granite 4.1 30B Nvfp4?

Granite 4.1 30B Nvfp4 requires approximately 16.1 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 4.1 30B Nvfp4 and how large is it?

Granite 4.1 30B Nvfp4 is developed by mlx-community, a model with 30b 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 4.1 30B Nvfp4?

Granite 4.1 30B Nvfp4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 4.1 30B Nvfp4 by mlx-community — VRAM 16.1GB, 128K context

Name: Granite 4.1 30B Nvfp4
Author: mlx-community

Granite 4.1 30B Nvfp4 is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 16.1GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

4-bit Base model:ibm-granite/granite... Base model:quantized:ibm-grani... Conversational Granite Granite-4.0 Language Mlx Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/granite-4.1-30b-nvfp4

Granite 4.1 30B Nvfp4 Parameters and Internals

LLM Name	Granite 4.1 30B Nvfp4
Repository 🤗	https://huggingface.co/mlx-community/granite-4.1-30b-nvfp4
Base Model(s)	ibm-granite/granite-4.1-30b ibm-granite/granite-4.1-30b
Model Size	30b
Required VRAM	16.1 GB
Updated	2026-07-31
Maintainer	mlx-community
Model Type	granite
Model Files	5.3 GB: 1-of-4 5.3 GB: 2-of-4 5.3 GB: 3-of-4 0.2 GB: 4-of-4
Model Architecture	GraniteForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.53.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	bfloat16
Errors	replace

Rank the Granite 4.1 30B Nvfp4 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 4.1 30B Nvfp4

Best Alternatives	Context / RAM	Downloads	Likes
...30B Claude 4.6 Opus Thinking X	128K / 58.6 GB	48	1
Granite 4.2 30B	128K / 58.2 GB	995	62
Granite 4.1 30B	128K / 57.8 GB	20845	138
Granite 4.1 30B Base	128K / 57.8 GB	1705	27
Granite 4.1 30B Mxfp4	128K / 15.3 GB	494	2
Granite 4.1 30B Mxfp8	128K / 29.8 GB	328	3
Granite 4.1 30B Bf16	128K / 57.4 GB	83	1
...6 Opus Thinking Charles Xavier	128K / 58.6 GB	35	3
Granite 4.1 30B	128K / 57.8 GB	56	0
Unsloth Granite 4.1 30B Mlx	128K / 57.4 GB	49	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-4.1-30b-nvfp4.