Hugging Face Forums
Too large to be loaded automatically (16GB > 10GB) issue with QWEN 2.5 VL 7B
Inference Endpoints on the Hub
John6666
April 15, 2025, 2:41am
2
Same here. Maybe related to this incident.
show post in topic
Related topics
Topic
Replies
Views
Activity
The model mistralai/Mistral-7B-Instruct-v0.1 is too large to be loaded automatically (14GB > 10GB)
Models
2
181
April 15, 2025
Inference service for large models, such as Vicuna 13b
Beginners
0
1427
May 5, 2023
Issue with ALLaM-7B Model in Inference API - Size Limitation Error
Inference Endpoints on the Hub
1
56
March 7, 2025
Cannot run large models using API token
Inference Endpoints on the Hub
5
7296
February 22, 2024
PRO Plan and for running huge models on free inference api?
Beginners
1
1803
May 15, 2023