Tencent Hy3
Tencent Hy3 is an open-weights language model from Tencent, released April 23, 2026. Its makers disclosed about 295B parameters.
Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data.
Check it against your own PC →
Can you run Tencent Hy3 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 | Size unknown | – | – | – | – |
| 8 GB VRAM | Size unknown | – | – | – | – |
| 12 GB VRAM | Size unknown | – | – | – | – |
| 16 GB VRAM | Size unknown | – | – | – | – |
| 24 GB VRAM | Size unknown | – | – | – | – |
| 32 GB VRAM | Size unknown | – | – | – | – |
Parameter count unknown. The weights may not be on Hugging Face yet.
Benchmark results
Epoch AI has not published results for Tencent Hy3 yet. New models are usually evaluated within days to weeks.
Links
More from Tencent
WeVisOne VL 4B · WeVisOne VL 2B · Hy Memory 30B A3B · Youtu Parsing Omni · Tencent Hy4 preview · Hy4 preview