Tencent has released a preview of its new open-weight language model, Hy4. This model boasts 770 billion total parameters and 49 billion active parameters, a significant increase from its predecessor, Hy3. Hy4 also features a 1 million token context window and supports two reasoning effort levels: 'high' and 'no_think'. Early testing with a prompt for an SVG of a pelican riding a bicycle revealed interesting reasoning traces, with the model considering and discarding options like helmets and sunglasses. AI
IMPACT Sets a new benchmark for parameter count and context window in open-weight models, potentially driving competition in large-scale LLM development.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →