CogVLM2 Models by Tsinghua Knowledge Engineering Group (THUDM)
1 model2025
Capabilities
MultimodalAll models
About
CogVLM2 is a family of 1 AI model by Tsinghua Knowledge Engineering Group (THUDM), released in 2025.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
CogVLM2 Chat 19BCurrent
Use when the workload needs 19B parameters and multimodal inputs.
2025-0419B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| CogVLM2 Chat 19B | Use when the workload needs 19B parameters and multimodal inputs. | 2025-04 | 19B parametersmultimodal inputs | Current |
Release Timeline
1 release group2025-04
1 current
CogVLM2 Chat 19B
Current19B parametersmultimodal inputs
Specifications(1 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| CogVLM2 Chat 19B | 2025-04 | 19B | Yes |
Frequently Asked Questions
- What is CogVLM2 used for?
- CogVLM2 is used for vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does CogVLM2 compare to ChatGLM-4?
- CogVLM2 by Tsinghua Knowledge Engineering Group (THUDM) is strongest where you need vision and multimodal work, while ChatGLM-4 by Tsinghua Knowledge Engineering Group (THUDM) is the closest related family to check for adjacent model selection. CogVLM2 has 1 listed variant, while ChatGLM-4 reaches up to 128k context, so compare the specs and pricing tables before choosing a production model.
- Which CogVLM2 model should I use?
- If price is the main constraint, use the pricing table first because CogVLM2 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate CogVLM2 Chat 19B with multimodal inputs.
