What are the hardware requirements for Lingshu 32B 4bit?

Lingshu 32B 4bit requires approximately 18.8 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 32B 4bit and how large is it?

Lingshu 32B 4bit is developed by mlx-community, a model with 32b 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 32B 4bit?

Lingshu 32B 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lingshu 32B 4bit by mlx-community — VRAM 18.8GB, 125K context

Name: Lingshu 32B 4bit
Author: mlx-community

Lingshu 32B 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 18.8GB, Context: 125K, License: mit, Quantized.

Model Card on HF 🤗: https://huggingface.co/mlx-community/Lingshu-32B-4bit

Lingshu 32B 4bit Parameters and Internals

LLM Name	Lingshu 32B 4bit
Repository 🤗	https://huggingface.co/mlx-community/Lingshu-32B-4bit
Model Size	32b
Required VRAM	18.8 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen2_5_vl
Model Files	5.3 GB: 1-of-4 5.4 GB: 2-of-4 5.3 GB: 3-of-4 2.8 GB: 4-of-4
Quantization Type	4bit
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	mit
Context Length	128000
Model Max Length	128000
Transformers Version	4.52.4
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Errors	replace

Rank the Lingshu 32B 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 Lingshu 32B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 VL 32B Instruct 4bit	125K / 19.8 GB	441	4
Qwen2.5 VL 32B Instruct 6bit	125K / 28 GB	77	1
Lingshu 32B 8bit	125K / 35.5 GB	27	1
Qwen2.5 VL 32B Instruct 8bit	125K / 36.2 GB	183	4
GTA1 32B	125K / 66.7 GB	191	6
Qwen2.5 VL 32B Instruct Bf16	125K / 67.3 GB	304	5