What are the hardware requirements for Granite 4.1 3B Mxfp8?

Granite 4.1 3B Mxfp8 requires approximately 3.5 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 3B Mxfp8 and how large is it?

Granite 4.1 3B Mxfp8 is developed by mlx-community, a model with 3b 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 3B Mxfp8?

Granite 4.1 3B Mxfp8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 4.1 3B Mxfp8 by mlx-community — VRAM 3.5GB, 128K context

Name: Granite 4.1 3B Mxfp8
Author: mlx-community

Granite 4.1 3B Mxfp8 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 3.5GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.24.

8-bit Base model:ibm-granite/granite... Base model:quantized:ibm-grani... Conversational Granite Granite-4.1 Language Mlx Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/granite-4.1-3b-mxfp8

Granite 4.1 3B Mxfp8 Parameters and Internals

LLM Name	Granite 4.1 3B Mxfp8
Repository 🤗	https://huggingface.co/mlx-community/granite-4.1-3b-mxfp8
Base Model(s)	ibm-granite/granite-4.1-3b ibm-granite/granite-4.1-3b
Model Size	3b
Required VRAM	3.5 GB
Updated	2026-08-10
Maintainer	mlx-community
Model Type	granite
Model Files	3.5 GB
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 3B Mxfp8 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 3B Mxfp8

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.1 3B	128K / 6.8 GB	328863	100
...anite 4.1 3B Medical Reasoning	128K / 6.8 GB	262	1
Granite 4.1 3B Base	128K / 6.8 GB	8994	21
Granite 4.1 3B Manumit V1	128K / 6.8 GB	134	0
Granite 4.1 3B	128K / 6.8 GB	2076	6
Granite 4.1 3B SFT Fable5	128K / 6.8 GB	468	0
Granite 4.1 3B Mxfp4	128K / 1.8 GB	758	3
...ranite 4.1 3B SFT Fable5 Glint	128K / 6.8 GB	58	0
Granite 4.1 3B Bf16	128K / 6.8 GB	93	1
Granite 4.1 3B Nvfp4	128K / 1.9 GB	37	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/granite-4.1-3b-mxfp8.