Get the app
LLM & Text Generation2 min reading time

Introducing Hy4 Preview

Simon Willison's Weblog
Read the full article
Tencent has released Hy4 Preview, a large language model with 770 billion parameters and a 1 million token context window, significantly larger than its predecessor Hy3. The model supports two reasoning effort levels and is available on Hugging Face with 1.56TB size.
#hugging-face#hy3#hy4#language-model-context-windows#large-language-models#model-parameter-scaling#tencent

More in LLM & Text Generation

LLM & Text Generation5 min read

PyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs

InfoQ (AI, ML & Data)
LLM & Text Generation5 min read

Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model

MarkTechPost
LLM & Text Generation5 min read

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost