What are the hardware requirements for Lingshu 7B?

Lingshu 7B requires approximately 16.6 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lingshu 7B and how large is it?

Lingshu 7B is developed by lingshu-medical-mllm, 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 Lingshu 7B?

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

Lingshu 7B by lingshu-medical-mllm — VRAM 16.6GB, 125K context

Name: Lingshu 7B
Author: lingshu-medical-mllm

Lingshu 7B is an open-source language model by lingshu-medical-mllm. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: mit, LLM Explorer Score: 0.23.

Arxiv:2506.07044 Clinical-reasoning Conversational Ct Endpoints compatible Fundus Histopathology Image-text-to-text Medical Mri Multimodal Qwen2 5 vl Radiology Region:us Report generation Safetensors Sharded Tensorflow X-ray

Model Card on HF 🤗: https://huggingface.co/lingshu-medical-mllm/Lingshu-7B

Lingshu 7B Parameters and Internals

LLM Name	Lingshu 7B
Repository 🤗	https://huggingface.co/lingshu-medical-mllm/Lingshu-7B
Model Size	7b
Required VRAM	16.6 GB
Updated	2026-08-09
Maintainer	lingshu-medical-mllm
Model Type	qwen2_5_vl
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.7 GB: 4-of-4
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	mit
Context Length	128000
Model Max Length	128000
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Lingshu 7B 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 Lingshu 7B

Best Alternatives	Context / RAM	Downloads	Likes
OmniLong Qwen2.5 VL 7B	512K / 16.6 GB	7	2
Qwen2.5 VL 7B Instruct	125K / 16.7 GB	8740905	1666
OlmOCR 2 7B 1025 FP8	125K / 10 GB	540426	253
OlmOCR 2 7B 1025	125K / 16.6 GB	244728	157
UI TARS 1.5 7B	125K / 33.2 GB	599881	605
RolmOCR	125K / 16.6 GB	224280	589
ICM R2	125K / 16.6 GB	27	4
Fara 7B	125K / 16.6 GB	2059	619
SpatialBlock 7B Direct	125K / 16.6 GB	49	0
Qwen2.5 VL 7B Instruct FP4	125K / 7.2 GB	49165	3

Note: green Score (e.g. "73.2") means that the model is better than lingshu-medical-mllm/Lingshu-7B.