Microsoft

TRELLIS Image Large

Image-to-3D model that produces textured meshes. Runs in ~12 GB VRAM and outputs glTF.

1.2B parameterstrellismit12GB - 12GB VRAM

About This Model

Microsoft's TRELLIS produces game-ready textured 3D meshes from a single reference image. The first open model that hits genuine production quality for image-to-3D, with output you can drop straight into Blender.

Check Your Hardware

See which quantizations of TRELLIS Image Large your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
FP16162.4 GB12 GB16 GB
100%

How to run TRELLIS Image Large

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

    JeffreyXiang/TRELLIS-image-large
  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 TRELLIS Image Large 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 TRELLIS Image Large?

TRELLIS Image Large requires 12GB VRAM minimum with FP16 quantization. For full precision, you need 12GB VRAM.

What is the best quantization for TRELLIS Image Large?

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