What are the hardware requirements for Unsloth Granite 4.1 30B Mlx?

Unsloth Granite 4.1 30B Mlx requires approximately 57.4 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 Unsloth Granite 4.1 30B Mlx and how large is it?

Unsloth Granite 4.1 30B Mlx is developed by Basher17, 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 Unsloth Granite 4.1 30B Mlx?

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

Unsloth Granite 4.1 30B Mlx by Basher17 — VRAM 57.4GB, 128K context

Name: Unsloth Granite 4.1 30B Mlx
Author: Basher17

Unsloth Granite 4.1 30B Mlx is an open-source language model by Basher17. Features: 30b LLM, VRAM: 57.4GB, Context: 128K, License: apache-2.0.

Base model:finetune:unsloth/gr... Base model:unsloth/granite-4.1... Conversational Endpoints compatible Granite Granite-4.0 Language Mlx Mlx-my-repo Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/Basher17/unsloth-granite-4.1-30b-mlx

Unsloth Granite 4.1 30B Mlx (Basher17/unsloth-granite-4.1-30b-mlx)

🌟 Advertise your project 🚀

Unsloth Granite 4.1 30B Mlx Parameters and Internals

LLM Name	Unsloth Granite 4.1 30B Mlx
Repository 🤗	https://huggingface.co/Basher17/unsloth-granite-4.1-30b-mlx
Base Model(s)	unsloth/granite-4.1-30b unsloth/granite-4.1-30b
Model Size	30b
Required VRAM	57.4 GB
Updated	2026-05-02
Maintainer	Basher17
Model Type	granite
Model Files	5.3 GB: 1-of-11 5.3 GB: 2-of-11 5.3 GB: 3-of-11 5.3 GB: 4-of-11 5.3 GB: 5-of-11 5.3 GB: 6-of-11 5.3 GB: 7-of-11 5.3 GB: 8-of-11 5.3 GB: 9-of-11 5.3 GB: 10-of-11 4.4 GB: 11-of-11
Model Architecture	GraniteForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.6
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100352
Torch Data Type	bfloat16
Errors	replace

Best Alternatives to Unsloth Granite 4.1 30B Mlx

Best Alternatives	Context / RAM	Downloads	Likes
Granite 4.1 30B	128K / 57.8 GB	287	0
Granite 4.1 30B	128K / 57.8 GB	124	37
Granite 4.1 30B Base	128K / 57.8 GB	29	18
Granite 4.1 30B Fp8	128K / 30.1 GB	218	5

Note: green Score (e.g. "73.2") means that the model is better than Basher17/unsloth-granite-4.1-30b-mlx.

Rank the Unsloth Granite 4.1 30B Mlx Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53373 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Unsloth Granite 4.1 30B Mlx by Basher17

» All LLMs » Basher17 » Unsloth Granite 4.1 30B Mlx URL Share it on

Unsloth Granite 4.1 30B Mlx Parameters and Internals

Best Alternatives to Unsloth Granite 4.1 30B Mlx

Rank the Unsloth Granite 4.1 30B Mlx Capabilities

What open-source LLMs or SLMs are you in search of? 53373 in total.