Theme
AI Resources
Hy4 preview
Hy4 preview is Tencent Hy Team's early release of a very large Mixture-of-Experts language model for coding, document and analysis work, game development, research, tool use, and long-context tasks.
Tencent lists 770B total parameters, 49B active parameters per token, a 1 million-token context window, public BF16 and FP8 weights, and dedicated deployment paths for vLLM and SGLang. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
A 770B-total MoE model
Hy4 preview has 49B active parameters per token across a 770B-parameter backbone. Tencent also builds in a multi-token-prediction layer for speculative decoding.
Why it stands out
One model for very large work contexts
Tencent positions the model around long-horizon software work, files and office artifacts, playable game prototypes, difficult research questions, and tool-driven tasks, with a 1M-token context window for large inputs.
Availability
Public weights, heavy deployment
The official Hugging Face pages host BF16 and FP8 checkpoints. Tencent's serving examples use the FP8 model with tensor parallelism across eight GPUs through dedicated vLLM or SGLang images.
Why it matters
What makes it useful
Hy4 preview puts an unusually large context window, a 49B-active MoE design, speculative decoding, and tool-call support into one inspectable model release. That gives model and infrastructure teams a concrete way to judge whether much more capacity and context are worth the storage, memory, and serving burden for their work.
What to know
Where it fits
It fits teams comparing flagship-scale public model weights for long coding sessions, large collections of files, complex artifacts, research, or tool-driven workflows. It is not a normal laptop model or a no-setup chatbot: the BF16 repository is about 1.56 TB, the FP8 repository is about 814 GB, and Tencent's serving examples use eight GPUs.
Notable points
What stands out
Tencent calls this an early version and says it can spend longer than necessary reasoning through complex tasks and over-verify its own work. Its productivity and benchmark results are project-reported evidence, including internal evaluations, rather than a universal ranking.
Before using
What to review
Start with the exact BF16 or FP8 model page and the matching current vLLM or SGLang recipe; the deployment examples use dedicated images and model-specific parsers.
Budget for hundreds of gigabytes of model files plus GPU memory, cache, runtime overhead, and eight-way tensor parallelism in the official examples.
Test whether the default high reasoning effort helps the task. Tencent documents a no-think setting for direct responses and separately warns that the preview may reason and verify for too long.
Review tool calls, generated code, documents, calculations, and game or research outputs before they affect a repository, business decision, public surface, or other real system.
The project identifies Apache-2.0. Review the current terms at the main official source for your intended use.
Reader fit
Who may find it relevant
Model and infrastructure teams with multi-GPU systems evaluating flagship-scale public weights.
Builders testing very long coding, document, analysis, research, or tool-driven workflows.
Teams comparing high-reasoning and direct-response modes behind an OpenAI-compatible local API.
Less relevant for readers seeking a small local model, a consumer chatbot, or image and video generation.
Editorial note
Why LifeHubber lists it
LifeHubber lists Hy4 preview because it makes a demanding model choice unusually concrete: 770B total parameters, 49B active parameters, a 1M-token context window, public BF16 and FP8 weights, and eight-GPU serving examples. Readers can weigh that capacity against the storage, hardware, and preview-stage behavior before choosing it for long, tool-heavy work.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Compare the preview with a smaller model and the wider model field.
Hy4 preview pushes model size and context much further than Hy3, while also demanding substantially heavier infrastructure. These paths help separate that scale choice from model-to-agent setup and other model options.
More in AI Models
Keep browsing this category
Explore more AI model resources.
Gemma 4
google/gemma-4
A Google DeepMind Gemma 4 model family collection with public checkpoints including Gemma 4 12B, a dense multimodal model Google describes around local agentic workflows, native audio input, and encoder-free vision/audio handling.
GLM-5.3
zai-org/GLM-5.3
Z.ai's 753B text-generation model for complex coding and long-horizon agent work, with public weights, an official 1M-token evaluation path, adjustable reasoning effort, and several technical serving options.
GLM-5.3-Flash
zai-org/GLM-5.3-Flash
A Z.ai 320B-total, 18B-active multimodal mixture-of-experts model for coding, agent workflows, visual input, and long-context work, with a 1M-token context window, public FP8 and BF16 weights, API access, and several technical serving paths.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
