Tencent

Hunyuan3D 2

Two-stage image-to-3D — shape generation then PBR texture synthesis. Strong topology.

2.5B parametershunyuan3dtencent-hunyuan16GB - 16GB VRAM

About This Model

Hunyuan3D 2 splits 3D generation into shape + texture stages. The PBR texture pass is what sets it apart — the meshes ship with realistic materials, not just colors baked into vertices.

Check Your Hardware

See which quantizations of Hunyuan3D 2 your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
FP16165 GB16 GB24 GB
100%

How to run Hunyuan3D 2

Pick a runtime — copy & paste. Commands are pre-filled with this model’s repo.

GUI. Browse → download → chat. MLX on Apple Silicon.

LM Studio home →
  1. 1

    Open LM Studio

    Go to the 🔍 Search tab.

  2. 2

    Search for

    tencent/Hunyuan3D-2
  3. 3

    Download

    Pick the FP16 quant — best balance of size vs. quality.

  4. 4

    Chat

    Hit ▶ Load Model and start chatting. Toggle 'Local Server' to expose an OpenAI-compatible API on :1234.

Community benchmarks

Real tokens/sec reports from people running Hunyuan3D 2 on actual hardware.

No community runs yet for this model. Be the first to submit your numbers.

Frequently Asked Questions

How much VRAM do I need to run Hunyuan3D 2?

Hunyuan3D 2 requires 16GB VRAM minimum with FP16 quantization. For full precision, you need 16GB VRAM.

What is the best quantization for Hunyuan3D 2?

Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.