What are the hardware requirements for Orvena 4B MLX 4bit?

Orvena 4B MLX 4bit requires approximately 3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Orvena 4B MLX 4bit and how large is it?

Orvena 4B MLX 4bit is developed by Orvena, a model with 4b 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 Orvena 4B MLX 4bit?

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

Orvena 4B MLX 4bit by Orvena — VRAM 3GB

Name: Orvena 4B MLX 4bit
Author: Orvena

Orvena 4B MLX 4bit is an open-source language model by Orvena. Features: 4b LLM, VRAM: 3GB, License: apache-2.0, Quantized.

4-bit 4bit Base model:orvena/orvena-4b Base model:quantized:orvena/or... Conversational Function-calling Image-text-to-text Iphone Mlx Multilingual On-device Quantized Qwen3 5 Region:us Safetensors Tool-use

Model Card on HF 🤗: https://huggingface.co/Orvena/Orvena-4B-MLX-4bit

Orvena 4B MLX 4bit Parameters and Internals

LLM Name	Orvena 4B MLX 4bit
Repository 🤗	https://huggingface.co/Orvena/Orvena-4B-MLX-4bit
Base Model(s)	Orvena 4B Orvena/Orvena-4B
Model Size	4b
Required VRAM	3 GB
Updated	2026-11-06
Maintainer	Orvena
Model Type	qwen3_5
Model Files	3.0 GB
Quantization Type	4bit
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Orvena 4B 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 Orvena 4B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 4B 3D Coder OptiQ 4bit	0K / 0.7 GB	416	1
Underdog Woof 4B 1.1	0K / 2.4 GB	1866	23
Kestrel 4B Coder OQ4e Fp16 Mtp	0K / 3.9 GB	198	1
Qwen3.5 4B MLX 4bit	0K / 3 GB	28023	32
Jugurtha 4B MLX 4bit	0K / 2.4 GB	157	2
H2o Lightning 4B Mlx Q8	0K / 5.1 GB	158	2
Sbzhanzhang	0K / 2.4 GB	230	1
LightOnOCR 3 4B 4bit	0K / 3 GB	177	1
Loopl 4B 4bit	0K / 3 GB	170	1
H2o Lightning 4B Mlx Q4	0K / 3 GB	95	1

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