What are the hardware requirements for Deepseek Vl2 Tiny?

Deepseek Vl2 Tiny requires approximately 6.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Vl2 Tiny and how large is it?

Deepseek Vl2 Tiny is developed by deepseek-ai, a model with 3.4b 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 Deepseek Vl2 Tiny?

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

Deepseek Vl2 Tiny by deepseek-ai — VRAM 6.7GB

Name: Deepseek Vl2 Tiny
Author: deepseek-ai

Deepseek Vl2 Tiny is an open-source language model by deepseek-ai. Features: 3.4b LLM, VRAM: 6.7GB, License: other, LLM Explorer Score: 0.27.

Arxiv:2412.10302 Deepseek vl v2 Endpoints compatible Image-text-to-text Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-vl2-tiny

Deepseek Vl2 Tiny Parameters and Internals

LLM Name	Deepseek Vl2 Tiny
Repository 🤗	https://huggingface.co/deepseek-ai/deepseek-vl2-tiny
Model Size	3.4b
Required VRAM	6.7 GB
Updated	2026-08-09
Maintainer	deepseek-ai
Model Type	deepseek_vl_v2
Model Files	6.7 GB: 1-of-1
Model Architecture	AutoModel
License	other
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<｜▁pad▁｜>
Torch Data Type	bfloat16

Rank the Deepseek Vl2 Tiny 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 Deepseek Vl2 Tiny

Best Alternatives	Context / RAM	Downloads	Likes
...E4B It Qat Mobile Transformers	0K / 3.5 GB	3032	22

Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/deepseek-vl2-tiny.