What are the hardware requirements for OmniLMM 12B?

OmniLMM 12B requires approximately 23.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OmniLMM 12B and how large is it?

OmniLMM 12B is developed by openbmb, a model with 12b 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 OmniLMM 12B?

OmniLMM 12B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OmniLMM 12B by openbmb — VRAM 23.2GB, 32K context

Name: OmniLMM 12B
Author: openbmb

OmniLMM 12B is an open-source language model by openbmb. Features: 12b LLM, VRAM: 23.2GB, Context: 32K, LLM Explorer Score: 0.11.

Arxiv:2308.12038 Arxiv:2312.00849 Arxiv:2403.11703 Dataset:haoyezhang/rlhf-v-data... Dataset:yirany/unimm-chat Endpoints compatible Omnilmm Pytorch Region:us Visual-question-answering

Model Card on HF 🤗: https://huggingface.co/openbmb/OmniLMM-12B

OmniLMM 12B Parameters and Internals

Model Type

visual-question-answering

Use Cases

Areas:

research, commercial applications

Primary Use Cases:

Real-time multimodal interaction

Training Details

Data Sources:

HaoyeZhang/RLHF-V-Dataset, Yirany/UniMM-Chat

Methodology:

Trained on multimodal data in a curriculum fashion with a perceiver resampler layer.

Model Architecture:

Built based on EVA02-5B and Zephyr-7B-β, and connected with a perceiver resampler layer.

LLM Name	OmniLMM 12B
Repository 🤗	https://huggingface.co/openbmb/OmniLMM-12B
Model Size	12b
Required VRAM	23.2 GB
Updated	2026-07-31
Maintainer	openbmb
Model Type	omnilmm
Model Files	23.2 GB
Model Architecture	OmniLMMForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32009
Torch Data Type	bfloat16

Rank the OmniLMM 12B 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 OmniLMM 12B

Best Alternatives	Context / RAM	Downloads	Likes
RLAIF V 12B	32K / 23.3 GB	13	8

Note: green Score (e.g. "73.2") means that the model is better than openbmb/OmniLMM-12B.