Hy4 preview
Hy4 preview is an open-weights language model from Tencent, released August 27, 2026. It has 780B parameters (mixture-of-experts, 50B active). The context window is 1M tokens.
Check it against your own PC →
Can you run Hy4 preview locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: 6block/Hy4-preview-GGUF · qtum/Hy4-preview-GGUF · anemll/Hy4-preview-FlashMoE-STQ1_0 · avar6/Hy4-Preview-gguf · Oxmiq/Hy4-preview-NVFP4-W4A16 · mlx-community/Hy4-preview-4bit
Benchmark results
Epoch AI has not published results for Hy4 preview yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: tencent/Hy4-preview
More from Tencent
WeVisOne VL 4B · WeVisOne VL 2B · Hy Memory 30B A3B · Youtu Parsing Omni · Tencent Hy4 preview · Tencent Hy3