WeMM-Video Models by Tencent AI Lab
Tencent AI Lab releases · 18 in the last 12 months · this family litChangelog →
4 models2026Up to 256K ctx
Last refreshed 2026-11-20. Next refresh: weekly.
Details
ResearcherTencent AI Lab
LicenseApache 2.0OSI-approved
Commercial usePermitted
Models4
Released2026
Max context256K
Capabilities
VisionAll models
MultimodalAll models
ReasoningAll models
Links
WebsiteAbout
Tencent WeChat Vision’s bilingual audio-visual understanding and reasoning models.
Decision facts
- Best fit
- vision and multimodal workreasoningcoding
- Capability starting point
- WeMM-Video 2B with 256K context and reasoning and multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Hunyuan Image
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view
WeMM-Video 2BCurrent
Use when the workload needs multimodal, 256K context, and 2B parameters.
2026-11multimodal256K context2B parameters
WeMM-Video 4BCurrent
Use when the workload needs multimodal, 256K context, and 4B parameters.
2026-11multimodal256K context4B parameters
WeMM-Video 9BCurrent
Use when the workload needs multimodal, 256K context, and 9B parameters.
2026-11multimodal256K context9B parameters
WeMM-Video 35B-A3BCurrent
Use when the workload needs multimodal, 256K context, and reasoning.
2026-11multimodal256K contextreasoning
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| WeMM-Video 2B | Use when the workload needs multimodal, 256K context, and 2B parameters. | 2026-11 | multimodal256K context2B parameters | Current |
| WeMM-Video 4B | Use when the workload needs multimodal, 256K context, and 4B parameters. | 2026-11 | multimodal256K context4B parameters | Current |
| WeMM-Video 9B | Use when the workload needs multimodal, 256K context, and 9B parameters. | 2026-11 | multimodal256K context9B parameters | Current |
| WeMM-Video 35B-A3B | Use when the workload needs multimodal, 256K context, and reasoning. | 2026-11 | multimodal256K contextreasoning | Current |
Release Timeline
1 release group2026-11
4 current
WeMM-Video 2B
Currentmultimodal256K context2B parameters
WeMM-Video 35B-A3B
Currentmultimodal256K contextreasoning
WeMM-Video 4B
Currentmultimodal256K context4B parameters
WeMM-Video 9B
Currentmultimodal256K context9B parameters
Specifications(4 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning |
|---|---|---|---|---|---|---|
| WeMM-Video 2B | 2026-11 | 256K | 2B | Yes | Yes | Yes |
| WeMM-Video 4B | 2026-11 | 256K | 4B | Yes | Yes | Yes |
| WeMM-Video 9B | 2026-11 | 256K | 9B | Yes | Yes | Yes |
| WeMM-Video 35B-A3B | 2026-11 | 256K | 35B (3B active) | Yes | Yes | Yes |

