What are the hardware requirements for Granite 4.2 3B MLX 4bit?

Granite 4.2 3B MLX 4bit requires approximately 2.1 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 4.2 3B MLX 4bit and how large is it?

Granite 4.2 3B MLX 4bit is developed by Orvena, 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 4.2 3B MLX 4bit?

Granite 4.2 3B MLX 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Granite 4.2 3B MLX 4bit by Orvena — VRAM 2.1GB, 128K context

Name: Granite 4.2 3B MLX 4bit
Author: Orvena

Granite 4.2 3B MLX 4bit is an open-source language model by Orvena. Features: 3b LLM, VRAM: 2.1GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

4-bit 4bit Base model:ibm-granite/granite... Base model:quantized:ibm-grani... Conversational Granite Granite-4.2 Mlx Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Orvena/granite-4.2-3b-MLX-4bit

Granite 4.2 3B MLX 4bit Parameters and Internals

LLM Name	Granite 4.2 3B MLX 4bit
Repository 🤗	https://huggingface.co/Orvena/granite-4.2-3b-MLX-4bit
Base Model(s)	ibm-granite/granite-4.2-3b ibm-granite/granite-4.2-3b
Model Size	3b
Required VRAM	2.1 GB
Updated	2026-08-27
Maintainer	Orvena
Model Type	granite
Model Files	2.1 GB
Quantization Type	4bit
Model Architecture	GraniteForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|im_end\|>
Vocabulary Size	100352
Torch Data Type	bfloat16
Errors	replace

Rank the Granite 4.2 3B MLX 4bit 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 4.2 3B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
TwIL LM3 Pro	128K / 2.2 GB	1774	38
Granite 4.2 3B	128K / 7.4 GB	1894	33
Granite 4.1 3B	128K / 6.8 GB	328863	100
Granite 4.2 3B Heretic	128K / 7.4 GB	908	0
Granite 4.2 3B Heretic	128K / 7.4 GB	626	1
Granite 4.1 3B Base	128K / 6.8 GB	8994	21
Granite 4.2 3B	128K / 7.4 GB	300	1
...e V1 Clm Nasasmd Granite4.1 3B	128K / 6.9 GB	203	1
Granite 4.1 3B	128K / 6.8 GB	2076	6
... Granite 4.1 3B Claude Fable 5	128K / 6.8 GB	545	1

Note: green Score (e.g. "73.2") means that the model is better than Orvena/granite-4.2-3b-MLX-4bit.