What are the hardware requirements for Cogvlm2 Video Llama3 Base?

Cogvlm2 Video Llama3 Base requires approximately 25.1 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Cogvlm2 Video Llama3 Base and how large is it?

Cogvlm2 Video Llama3 Base is developed by THUDM, a model with 12.5b 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 Cogvlm2 Video Llama3 Base?

Cogvlm2 Video Llama3 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Cogvlm2 Video Llama3 Base by THUDM — VRAM 25.1GB, 2K context

Name: Cogvlm2 Video Llama3 Base
Author: THUDM

Cogvlm2 Video Llama3 Base is an open-source language model by THUDM. Features: 12.5b LLM, VRAM: 25.1GB, Context: 2K, License: other, LLM Explorer Score: 0.13.

Chat Cogvlm--video Cogvlm2 Conversational Custom code En Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/zai-org/cogvlm2-video-llama3-base

Cogvlm2 Video Llama3 Base Parameters and Internals

LLM Name	Cogvlm2 Video Llama3 Base
Repository 🤗	https://huggingface.co/zai-org/cogvlm2-video-llama3-base
Model Size	12.5b
Required VRAM	25.1 GB
Updated	2026-08-08
Maintainer	THUDM
Model Files	5.0 GB: 1-of-6 5.0 GB: 2-of-6 4.9 GB: 3-of-6 5.0 GB: 4-of-6 4.1 GB: 5-of-6 1.1 GB: 6-of-6
Supported Languages	en
Model Architecture	CogVLMVideoForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.43.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Cogvlm2 Video Llama3 Base 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 Cogvlm2 Video Llama3 Base

Best Alternatives	Context / RAM	Downloads	Likes
VisionReward Video	2K / 25.1 GB	1979	8
VisionReward Video	2K / 25.1 GB	877	5
Cogvlm2 Video Llama3 Chat	2K / 25.1 GB	1110	51
Cogvlm2 Video Llama3 Chat	2K / 25.1 GB	136	56
Cogvlm2 Video Llama3 Base	2K / 25.1 GB	9	1

Note: green Score (e.g. "73.2") means that the model is better than zai-org/cogvlm2-video-llama3-base.