What are the hardware requirements for Llava Med 7B Delta?

Llava Med 7B Delta requires approximately 13.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llava Med 7B Delta and how large is it?

Llava Med 7B Delta is developed by microsoft, a model with 7b 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 Llava Med 7B Delta?

Llava Med 7B Delta is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llava Med 7B Delta by microsoft — VRAM 13.5GB

Name: Llava Med 7B Delta
Author: microsoft

Llava Med 7B Delta is an open-source language model by microsoft. Features: 7b LLM, VRAM: 13.5GB, License: other, LLM Explorer Score: 0.1.

Arxiv:2306.00890 Endpoints compatible Llava Medical Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/microsoft/llava-med-7b-delta

Llava Med 7B Delta Parameters and Internals

Model Type

large language model, vision model

Use Cases

Areas:

research, biomedical vision-language processing

Primary Use Cases:

Supporting AI researchers in biomedical vision-language processing

Limitations:

Not suitable for clinical care or decision making

Additional Notes

Users need to apply delta weights on top of the original LLaMA weights to get actual LLaVA weights.

Training Details

Data Sources:

PMC-15M dataset

Methodology:

Curriculum learning for adapting LLaVA to the biomedical domain.

Training Time:

One day

LLM Name	Llava Med 7B Delta
Repository 🤗	https://huggingface.co/microsoft/llava-med-7b-delta
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-07-23
Maintainer	microsoft
Model Type	llava
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2
Model Architecture	LlavaLlamaForCausalLM
License	other
Model Max Length	1024
Transformers Version	4.28.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32004
Torch Data Type	float16

Rank the Llava Med 7B Delta 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 Llava Med 7B Delta

Best Alternatives	Context / RAM	Downloads	Likes
Llava Merged Finetuned 7b	32K / 15.1 GB	1	1
Llava V1.6 Mistral 7B PATCHED	32K / 15.1 GB	17	8
KoLLaVA V1.5 Synatra 7B	32K / 15.1 GB	13	8
Llava V1.5 7B	4K / 13.5 GB	219094	557
Llava V1.6 Vicuna 7B	4K / 14.1 GB	19939	144
...va 1.5 Image Classification V3	4K / 23.3 GB	224	0
Vlm Rlaif Video Llava 7b	4K / 14.2 GB	6	0
Table Llava V1.5 7B	4K / 14.2 GB	9	13
Llava V1.5 7B M3	4K / 14.1 GB	93	2
Som Llava V1.5 7B	4K / 14.1 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than microsoft/llava-med-7b-delta.