Is there any model that practically compares to Sonnet 4.6 in code and vision and runs on home-grade (12G-24G) cards?

im currently running a custom Gemma4 26b MoE model on my 24gb m2... super fast and it beat deepseek, chatgpt, and gemini in 3 different puzzles/code challenges I tested it on. the issue now is the low context... I can only do 2048 tokens with my vram... the gap is slowly closing on the frontier models