Bobo Li on X: "We just released OneJev 🔥, an open multimodal System One decision model. 🌐 https://t.co/vuGgdinslu 1. OneJev-27B matches the official Jev on TypeSafe (89.3 vs 89.0), while OneJev-0.8B already outperforms Jev-Omni 12B (70.0 vs 60.8). 💻 https://t.co/0r5fUxjpNE 2. OneJev works with screenshots, photos, video, and text, and comes in four sizes: 0.8B / 4B / 9B / 27B. 3. OneJev is built for fast, repeated decisions. On one H200, OneJev-0.8B takes just 31 ms for one question. OneJev-4B takes 64 ms for one question and 104 ms for ten questions. 4. More details 🤗 https://t.co/KdLk9LgNQS 💻 https://t.co/0r5fUxjpNE 🌐 https://t.co/vuGgdinslu Built on Qwen3.5 and Qwen3.8. Thanks @Alibaba_Qwen for the open base models 🙏"

Bobo Li

@Bobo_hashtag

We just released OneJev 🔥, an open multimodal System One decision model. 🌐 omnijev.github.io/OneJev/ 1. OneJev-27B matches the official Jev on TypeSafe (89.3 vs 89.0), while OneJev-0.8B already outperforms Jev-Omni 12B (70.0 vs 60.8). 💻 github.com/OmniJev/OneJev 2. OneJev works with screenshots, photos, video, and text, and comes in four sizes: 0.8B / 4B / 9B / 27B. 3. OneJev is built for fast, repeated decisions. On one H200, OneJev-0.8B takes just 31 ms for one question. OneJev-4B takes 64 ms for one question and 104 ms for ten questions. 4. More details 🤗 huggingface.co/OmniJev/OneJev 💻 github.com/OmniJev/OneJev 🌐 omnijev.github.io/OneJev/ Built on Qwen3.5 and Qwen3.8. Thanks @Alibaba_Qwen for the open base models 🙏

3:31 PM · Sep 27, 2026·

115

Views

5

4