Model Releases
Good guy DeepSeek gives us accelerated models The most interesting one here is Gemma4-12B, I presume vision included. Might be the best loca…
Good guy DeepSeek gives us accelerated models The most interesting one here is Gemma4-12B, I presume vision included. Might be the best local model in its weight class now, by some margin Qwen 3.5 not
Good guy DeepSeek gives us accelerated models The most interesting one here is Gemma4-12B, I presume vision included. Might be the best local model in its weight class now, by some margin Qwen 3.5 not included because DS[park] doesn't do linear attention I guess
Source: Clem Delangue (X) | 2026-06-28