Reactions
7 postsAD 
Alexander Doria@DorialexanderNew competitive European model (30bA3b) from Soofi with SYNTH inside. https://twitter.com/effi288/status/2075904321707798699
- likes: 186
- replies: 5
- bookmarks: 92
- reposts: 15
LA Lisan al Gaib@scaling01germans released a model that's actually not terrible it's small, and still worse than Qwen3.5, but it's very comparable to Nemotron 3 Nano but I guess that's what 27T pre-training tokens will do to a model https://twitter.com/effi288/status/2075904321707798699
- likes: 751
- replies: 23
- bookmarks: 302
- reposts: 41
LB Lucas Beyer (bl16)@giffmana@scaling01 That's because it basically *is* nemotron 3 nano. It's a good exercise to get started though, looking forward to future ones.
- likes: 56
- replies: 2
- bookmarks: 2
- reposts: 0
LA Lisan al Gaib@scaling01there's more to come Nemotron 3 Super equivalent model https://x.com/effi288/status/2076305922327011368
- likes: 25
- replies: 0
- bookmarks: 3
- reposts: 0
AD Alexander Doria@DorialexanderFor anyone wondering why they did not post-train this is actual sovereignty in the good sense of the world: slowly building strategic autonomy up to the pretraining level, while having the humility to start from the best practices in the open.…
- likes: 148
- replies: 3
- bookmarks: 33
- reposts: 10
T( Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTex> 🇩🇪 Trained end-to-end on Deutsche Telekom’s Industrial AI Cloud in Munich — sovereign AI infrastructure on German soil Unexpected German W! https://twitter.com/effi288/status/2075904321707798699
- likes: 314
- replies: 8
- bookmarks: 74
- reposts: 21