ok I had to try: same demo, open model.
This is a AI post classified by Jev as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.
ok I had to try: same demo, open model. DiffusionGemma 26B-A4B + vLLM PR #57250 (structured reads) on my own custom endpoint. Using Matt's exact same sentences 👀 Mostly the same answers, a few fun misses (it thinks Luigi is blue 😂)
Posted by Victor M (30.7k followers) 1 h ago · 18 likes · 1.6k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Update: next checkpoint has effectively reached Jev calibration parity on MMLU! Also 8… — @4rcherhume
- Updated checkpoint coming soon. Much better calibration across text and image w/ better… — @4rcherhume
- This looks... interesting 👀 — @MiaAI_lab
- 🚨 DeepSeek V5 Leak: Beats Astra — @Priyannkaaaa
- Yes we are a healthcare company. Yes we just released the best open-weight alternative… — @4rcherhume
- Qwen又发大招了，Qwen-Image-2.1开源了，这是一个7B参数的文生图模型，对本地图像生成模型部署具有史诗级意义 — @xueyu1125
- Pirate Face activity · 21 Sept 2026 — @thepirateface
- Qwen-image-2.1 running on one of my DGX Sparks — @MichaelGannotti
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 38.2k posts from 4.9k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 09:50 UTC. Full method.