InternLM-XComposer2 Models by Intern-AI
Last refreshed 2026-04-19. Next refresh: weekly.
Details
About
The InternLM-XComposer2 family brings together a suite of vision-language large models (VLLMs) based on the InternLM2 foundation model. These models are adept at tackling advanced text-image comprehension and composition tasks, with variations such as the InternLM-XComposer2-VL excelling in multimodal benchmarks and InternLM-XComposer2 tailored for sophisticated text-image composition. A standout in this series, the InternLM-XComposer2.5, offers capabilities comparable to GPT-4V with just a 7B LLM backend, while the InternLM-XComposer2-4KHD can comprehend images up to 4K resolution. Open-source and accessible on Hugging Face and GitHub, these models cater to various needs, including multimodal content creation and enhancing visual language understanding, with some versions optimized for devices with limited resources through 4-bit quantization.
Decision facts
- Best fit
- coding
- Capability starting point
- InternLM XComposer2 4KHD 7B
- Lowest tracked input
- Not tracked
- Closest related family
- InternVL
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| InternLM XComposer2 4KHD 7B | Use when the workload needs 7B parameters. | 2024-04 | 7B parameters | Current |
| InternLM XComposer2 7B | Use when the workload needs 7B parameters. | 2024-04 | 7B parameters | Current |
| InternLM XComposer2 VL 7B | Use when the workload needs 7B parameters. | 2024-04 | 7B parameters | Current |
Release Timeline
1 release groupSpecifications(3 models)
| Model | Released | Parameters |
|---|---|---|
| InternLM XComposer2 4KHD 7B | 2024-04 | 7B |
| InternLM XComposer2 7B | 2024-04 | 7B |
| InternLM XComposer2 VL 7B | 2024-04 | 7B |
