# RSI-Jev v7.0-VL 4B decision model by Shanghua Gao > RSI-Jev v7.0-VL 4B returns typed decisions on text and images. Read its early exits, public weights, reported scores and serving limits. Updated 2026-11-07 (Australia/Adelaide) ## Quick answers ### What is RSI-Jev v7.0-VL 4B by Shanghua Gao? [RSI-Jev v7.0-VL 4B](): A Qwen3.5-4B decision fine-tune with text exits at layers 16, 20 and 32. [RSI-Jev v7.0-VL 4B facts]() [Source]() ### Who makes RSI-Jev v7.0-VL 4B? [RSI-Jev v7.0-VL 4B](): Shanghua Gao [RSI-Jev v7.0-VL 4B facts]() [Source]() ### Are RSI-Jev v7.0-VL 4B's weights open? [RSI-Jev v7.0-VL 4B](): Public weights with the RSI-Jev runtime; no causal prefix cache Licence: Apache-2.0 [RSI-Jev v7.0-VL 4B facts]() [Source]() By Shanghua Gao · Hugging Face package release: 2026-11-05 · OPEN A Qwen3.5-4B decision fine-tune with text exits at layers 16, 20 and 32. It reads a document and up to four images, then returns option probabilities without generating text. Image questions always use all 32 layers. Its own serving package supplies the option echo and bidirectional attention required by the weights. ## Facts - Size: 4.69B parameters; about 9.7 GB packaged weights - Inputs: Text and up to four images; choice, noul and score - Licence: Apache-2.0 - Limits: 32,768 tokens; up to 5,120 options; overlength requests get HTTP 422 - Access: Public weights with the RSI-Jev runtime; no causal prefix cache ## Claims and sources - **VENDOR-REPORTED**: The maker reports 60.63 on the public Decision Index 0.3, with 29.4 ms median and 236 ms p95 on one RTX PRO 6000 Blackwell at default effort. This is a public-suite run, not the full private index. Training used one seed and unreleased data. Ambiguous KoBBQ questions and some medicine and customer-support tasks regress against v6.1-VL. [source]() ## Links - [Source: Model card and files]() ## Related projects No related projects are listed in the registry.