SOURCE-REVIEWED MODEL PROFILE
Qwen3.5-4B
Post-trained vision-language checkpoint; base dependency for Tencent WeVisForensics. This catalogue addition is not a new-release claim.

Metadata reviewed 2026-11-20 · Original creator: Qwen
What it does
- Text and image inputs
- Hybrid attention architecture
- Dependency of the separately released WeVisForensics adapters
Local fit
Device fit depends on precision, context and runtime; no local test. Base checkpoint and agent adapters are separate artifacts. A small parameter label does not establish end-to-end detector memory requirements.
Native context specified by publisher. Extended context configurations require separate validation and memory.
Evidence and limits
Source reviewed; no local inference, forensic evaluation or hardware benchmark.
Publisher workflow documented; not independently tested
License and source
Published artifact LICENSE is Apache-2.0; separate dependencies retain their own terms.
Read the original model card ↗
Reviewed source revision: 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a