LLM EXPLORER 55,709 MODELS INDEXED

Lingshu 32B 8bit by mlx-community

By mlx-community · 27 downloads
HF Repo ↗ Copy URL

Lingshu 32B 8bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 35.5GB, Context: 125K, License: mit, Quantized.

  8bit   Clinical-reasoning   Conversational   Ct   Endpoints compatible   Fundus   Histopathology   Image-text-to-text   Medical   Mlx   Mri   Multimodal   Quantized   Qwen2 5 vl   Radiology   Region:us   Report generation   Safetensors   Sharded   Tensorflow   X-ray
Model Card on HF 🤗: https://huggingface.co/mlx-community/Lingshu-32B-8bit 

Lingshu 32B 8bit Parameters and Internals

LLM NameLingshu 32B 8bit
Repository 🤗https://huggingface.co/mlx-community/Lingshu-32B-8bit 
Model Size32b
Required VRAM35.5 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen2_5_vl
Model Files  5.2 GB: 1-of-7   5.3 GB: 2-of-7   5.3 GB: 3-of-7   5.4 GB: 4-of-7   5.4 GB: 5-of-7   5.3 GB: 6-of-7   3.6 GB: 7-of-7
Quantization Type8bit
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licensemit
Context Length128000
Model Max Length128000
Transformers Version4.52.4
Padding Token<|endoftext|>
Vocabulary Size152064
Errorsreplace

Best Alternatives to Lingshu 32B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Lingshu 32B 4bit125K / 18.8 GB612
Qwen2.5 VL 32B Instruct 4bit125K / 19.8 GB4414
Qwen2.5 VL 32B Instruct 6bit125K / 28 GB771
Qwen2.5 VL 32B Instruct 8bit125K / 36.2 GB1834
GTA1 32B125K / 66.7 GB1916
Qwen2.5 VL 32B Instruct Bf16125K / 67.3 GB3045