What are the hardware requirements for MiniCPM V 4 5 AWQ?

MiniCPM V 4 5 AWQ requires approximately 7.1 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiniCPM V 4 5 AWQ and how large is it?

MiniCPM V 4 5 AWQ is developed by openbmb, a model with 8.7b 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 MiniCPM V 4 5 AWQ?

MiniCPM V 4 5 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniCPM V 4 5 AWQ by openbmb — VRAM 7.1GB, 40K context

Name: MiniCPM V 4 5 AWQ
Author: openbmb

MiniCPM V 4 5 AWQ is an open-source language model by openbmb. Features: 8.7b LLM, VRAM: 7.1GB, Context: 40K, Quantized, LLM Explorer Score: 0.29.

Arxiv:2403.11703 4-bit Awq Base model:openbmb/minicpm-v-4... Base model:quantized:openbmb/m... Conversational Custom code Dataset:openbmb/rlaif-v-datase... Feature-extraction Image-text-to-text Minicpm-v Minicpmv Multi-image Multilingual Ocr Quantized Region:us Safetensors Sharded Tensorflow Video Vision

Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM-V-4_5-AWQ

MiniCPM V 4 5 AWQ Parameters and Internals

LLM Name	MiniCPM V 4 5 AWQ
Repository 🤗	https://huggingface.co/openbmb/MiniCPM-V-4_5-AWQ
Base Model(s)	MiniCPM V 4 5 openbmb/MiniCPM-V-4_5
Model Size	8.7b
Required VRAM	7.1 GB
Updated	2026-08-09
Maintainer	openbmb
Model Type	minicpmv
Model Files	4.8 GB: 1-of-2 2.3 GB: 2-of-2
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MiniCPMV
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.0
Tokenizer Class	MiniCPMVTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	151748
Torch Data Type	bfloat16
Errors	replace

Rank the MiniCPM V 4 5 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 MiniCPM V 4 5 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM V 4 5	40K / 17.4 GB	473360	1098

Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM-V-4_5-AWQ.