CogVLM2 Models by Tsinghua Knowledge Engineering Group (THUDM)
Tsinghua Knowledge Engineering Group (THUDM) releases · 1 in the last 12 monthsChangelog →
1 model2025
Last refreshed 2026-04-18. Next refresh: weekly.
Capabilities
MultimodalAll models
About
CogVLM2 is a family of 1 AI model by Tsinghua Knowledge Engineering Group (THUDM), released in 2025.
Decision facts
- Best fit
- vision and multimodal work
- Capability starting point
- CogVLM2 Chat 19B with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- ChatGLM-4
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 |
