LiveUpdated 2026-09-21 21:52 UTC
Deepseek Harness Now Has Image and Video Generations Built in with Qwen 2.1 and Minimax H3
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.
Deepseek Harness Now Has Image and Video Generations Built in with Qwen 2.1 and Minimax H3
Posted by Tech2Wild (4.1k followers) 1 h ago · 34 likes · 2k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- Aikido just drop (Altar-1) first open-weight Cyber-security model on HF & you can run… — @0x0SojalSec
- Meet Needle3, a text-generation model built for tool and function calling. It runs fully… — @HuggingModels
- impressive! — @AdamHoltererer
- The number one trending model on HF is an open-source multilingual system 1 decision… — @ClementDelangue
- Meet Altworld/Hemmingway-1, a text-generation model built on the Qwen3.5 text… — @HuggingModels
- 🚨 Xiaomi dropped MiMo-V2.6 today. Both open weights 👀 — @Tech2Wild
- 🚨 Xiaomi just dropped MiMo-V2.6, open weights 👀 — @Tech2Wild
- Xiaomi MiMo v2.6 Pro is the best open weight model in the world, almost on par with GPT… — @cheatyyyy
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. 40.3k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 21:52 UTC. Full method.