What are the hardware requirements for Deepseek Vl2 6bit?

Deepseek Vl2 6bit requires approximately 22.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Vl2 6bit and how large is it?

Deepseek Vl2 6bit is developed by mlx-community, a model with 6.1b 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 Deepseek Vl2 6bit?

Deepseek Vl2 6bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Vl2 6bit by mlx-community — VRAM 22.6GB

Name: Deepseek Vl2 6bit
Author: mlx-community

Deepseek Vl2 6bit is an open-source language model by mlx-community. Features: 6.1b LLM, VRAM: 22.6GB, License: other, Quantized.

6bit Conversational Deepseek vl v2 Endpoints compatible Image-text-to-text Mlx Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/deepseek-vl2-6bit

Deepseek Vl2 6bit Parameters and Internals

LLM Name	Deepseek Vl2 6bit
Repository 🤗	https://huggingface.co/mlx-community/deepseek-vl2-6bit
Model Size	6.1b
Required VRAM	22.6 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	deepseek_vl_v2
Model Files	5.3 GB: 1-of-5 5.4 GB: 2-of-5 5.2 GB: 3-of-5 5.4 GB: 4-of-5 1.3 GB: 5-of-5
Quantization Type	6bit
Model Architecture	AutoModel
License	other
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<｜▁pad▁｜>
Torch Data Type	bfloat16

Rank the Deepseek Vl2 6bit 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