No exact results. Similar results found.
@michabbb@social.vivaldi.net2026-10-29 17:45:08
⚙️ Architecture: 128 routed experts with 4 active per token plus 1 shared expert, a 1M token context window, and text image input via a Pixtral-style vision encoder that handles variable image sizes and aspect ratios
🎚️ One set of weights covers instruction following, reasoning, coding and agentic work. Reasoning effort is set per request: low, medium or high (default). Native function calling, JSON output and strict JSON schema enforcement