Model Releases
Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though!
Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though! 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more ef
Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though! 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6
Related
- 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with …
- DeepSeek debuts DeepSeek-V4.1-Flash, its smallest model built on its new Causal Encoder-Decoder architecture, with 552B backbone parameters and 1M-token context (Reuters)
- DeepSeek V4.1 Flash: Stronger, Faster, More Accessible
Source: Sebastian Raschka (X) | 2026-09-10