What are the hardware requirements for InternVL2 5 78B MPO AWQ?

InternVL2 5 78B MPO AWQ requires approximately 52.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternVL2 5 78B MPO AWQ and how large is it?

InternVL2 5 78B MPO AWQ is developed by OpenGVLab, a model with 78b 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 InternVL2 5 78B MPO AWQ?

InternVL2 5 78B MPO AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternVL2 5 78B MPO AWQ by OpenGVLab — VRAM 52.9GB

Name: InternVL2 5 78B MPO AWQ
Author: OpenGVLab

InternVL2 5 78B MPO AWQ is an open-source language model by OpenGVLab. Features: 78b LLM, VRAM: 52.9GB, License: other, Quantized, LLM Explorer Score: 0.16.

Arxiv:2312.14238 Arxiv:2404.16821 Arxiv:2411.10442 Arxiv:2412.05271 Awq Base model:opengvlab/internvl2... Base model:quantized:opengvlab... Conversational Custom code Dataset:opengvlab/mmpr-v1.1 Feature-extraction Image-text-to-text Internvl Internvl chat Multilingual Pytorch Quantized Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO-AWQ

InternVL2 5 78B MPO AWQ Parameters and Internals

LLM Name	InternVL2 5 78B MPO AWQ
Repository 🤗	https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO-AWQ
Base Model(s)	InternVL2 5 78B MPO OpenGVLab/InternVL2_5-78B-MPO
Model Size	78b
Required VRAM	52.9 GB
Updated	2026-08-08
Maintainer	OpenGVLab
Model Type	internvl_chat
Model Files	2.0 GB: 1-of-27 2.0 GB: 2-of-27 2.0 GB: 3-of-27 2.0 GB: 4-of-27 2.0 GB: 5-of-27 2.5 GB: 6-of-27 1.9 GB: 7-of-27 1.9 GB: 8-of-27 2.0 GB: 9-of-27 2.0 GB: 10-of-27 1.9 GB: 11-of-27 2.0 GB: 12-of-27 2.0 GB: 13-of-27 1.9 GB: 14-of-27 2.0 GB: 15-of-27 2.0 GB: 16-of-27 1.9 GB: 17-of-27 2.0 GB: 18-of-27 2.0 GB: 19-of-27 1.9 GB: 20-of-27 2.0 GB: 21-of-27 2.0 GB: 22-of-27 1.9 GB: 23-of-27 2.0 GB: 24-of-27 2.0 GB: 25-of-27 2.5 GB: 26-of-27 0.6 GB: 27-of-27
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	InternVLChatModel
License	other
Model Max Length	8192
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	float16
Errors	replace

Rank the InternVL2 5 78B MPO AWQ 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 InternVL2 5 78B MPO AWQ

Best Alternatives	Context / RAM	Downloads	Likes
InternVL3 78B AWQ	0K / 52.9 GB	464111	11
InternVL2 5 78B AWQ	0K / 52.9 GB	105	14
InternVL2 5 78B MPO	0K / 157.4 GB	37	55

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/InternVL2_5-78B-MPO-AWQ.