Before you start

AMD support for TRELLIS.2 moved during 2026 from isolated experiments to several parallel routes: a ROCm source fork, a patched ComfyUI stack, an in-progress Windows effort, and a native C++ implementation with ROCm and Vulkan backends. None of them are official support. This page keeps them separated and labels each card and runtime combination by how much evidence stands behind it.

Prerequisites

  • Your exact card model and its VRAM size, not just the family name
  • Your GPU's gfx compile target, since kernels are built per architecture
  • A decision on Linux or Windows before choosing a runtime
  • Acceptance that every AMD route here is community-maintained

Compatibility matrix

Columns are runtimes, rows are cards. A cell states how much evidence exists for that combination — not that the run will finish on your machine. Card names link to a page with the full reasoning.

Compatibility matrixReviewed 2026-08-15
GPUVRAMISAROCm forkLinuxComfyUI LinuxLinuxComfyUI WindowsWindows 11trellis.cpp ROCmLinux · Windowstrellis.cpp VulkanLinux · Windows
RDNA 4 gfx1200 · gfx1201
RX 9070 XT16 GBgfx1201TestedExpectedReportedExpectedExpected
RX 907016 GBgfx1201ExpectedExpectedExpectedExpectedExpected
RX 9060 XT16 GBgfx1200ExpectedUnknownUnknownExpectedExpected
RDNA 3 gfx1100 · gfx1101 · gfx1102
RX 7900 XTX24 GBgfx1100ExpectedTestedUnknownExpectedExpected
RX 7900 XT20 GBgfx1100ExpectedExpectedUnknownExpectedExpected
RX 7800 XT16 GBgfx1101ExpectedExpectedUnknownExpectedExpected
RX 7700 XT12 GBgfx1101UnknownExpectedUnknownExpectedExpected
RX 7600 XT16 GBgfx1102UnknownExpectedUnknownExpectedExpected
RDNA 3.5 gfx1150 · gfx1151
Ryzen AI Max+ 39596 GBgfx1151UnknownReportedReportedExpectedTested
RDNA 2 gfx1030 · gfx1031 · gfx1032
RX 6900 XT16 GBgfx1030UnknownUnknownBlockedUnknownExpected
  • Tested

    A named project or maintainer reports this exact card completing the pipeline end to end.

  • Reported

    Community reports exist but come from work in progress, partial runs, or a single tester.

  • Expected

    Inferred from a shared instruction set with a tested card. No direct report yet.

  • Blocked

    A known dependency, kernel, or runtime gap prevents this path today.

  • Unknown

    No usable report either way. Treat as untested rather than as a failure.

Every AMD route on this page is community or third-party work. Neither Microsoft nor AMD lists TRELLIS.2 as an officially supported workload, and AMD's own documentation still limits Windows to PyTorch rather than the full ROCm stack.

Tested route

TRELLIS.2 ROCm source fork

A fork of the upstream repository that ships HIP builds of FlexGEMM, CuMesh, nvdiffrast and nvdiffrec, plus a setup script that detects CUDA or ROCm and installs the matching dependencies. Validated on an RX 9070 XT 16 GB.

OS
Linux
Stack
ROCm 7.2 · PyTorch rocm7.2 · Python 3.10+
Python runtime
Required
Open the guide →
Tested route

ComfyUI + ROCm on Linux

The community ComfyUI wrapper plus a patch set that fixes the hardcoded GPU architecture flag, package paths and checkpoint downloads. Reported working end to end on a 7900 XTX for both shape-only and textured runs.

OS
Linux
Stack
ROCm 7.2.2 · PyTorch 2.11+rocm7.2 · Python 3.10–3.12
Python runtime
Required
Open the guide →
Work in progress

ComfyUI + ROCm on Windows

Work in progress. RDNA 4 is confirmed running and testers are being recruited; RDNA 3 and RDNA 3.5 are next in line. The maintainer warns about silent bugs that can change the final output without raising an error.

OS
Windows 11
Stack
PyTorch 2.9.1 + ROCm 7.2.1, or PyTorch 2.12 + ROCm 7.14 · Python 3.12
Python runtime
Required
Open the guide →
Tested route

trellis.cpp — ROCm build

A native C++/GGML reimplementation of the whole TRELLIS.2 pipeline. Prebuilt ROCm archives are published for Linux and Windows, which removes the CUDA-only Python wheels from the problem entirely.

OS
Linux · Windows
Stack
Prebuilt ROCm/HIP binaries · no Python runtime
Python runtime
Not required
Open the guide →
Tested route

trellis.cpp — Vulkan build

The path with the fewest prerequisites: a Vulkan-capable driver replaces the entire ROCm stack. The project reports Vulkan as its fastest backend on some integrated GPUs.

OS
Linux · Windows
Stack
Vulkan driver only · no ROCm, no Python runtime
Python runtime
Not required
Open the guide →
Weight formatWeights on diskPractical VRAMQuality noteWhere it comes from
f16 / bf16 (default)≈ 16.5 GB24 GB comfortableReference output. Everything else is measured against this.trellis.cpp default; safetensors in the ComfyUI and source routes.
Q8≈ 9.5 GB16 GB practicalDescribed by the project as visually near-lossless.trellis.cpp v0.5.4 and later.
Q4≈ 6 GB12 GB practical, 8 GB tightSlight texture graininess, aimed explicitly at lower-VRAM systems.trellis.cpp v0.5.4 and later.
GGUF K-quants (Q4_K_M – Q6_K)≈ 6 GB – 8 GB8 GB reported workableLoader-dependent. Compatibility follows the custom node, not the file name.ComfyUI GGUF loaders in the ROCm install guide.

Step by step

Identify the compile target, not just the card

ROCm builds kernels per instruction set. Navi 31 is gfx1100, Navi 32 is gfx1101, Navi 33 is gfx1102, Navi 48 is gfx1201 and Navi 44 is gfx1200. Two cards in the same marketing tier can need different builds, and at least one community wrapper ships with a hardcoded architecture flag that has to be corrected by hand.

You can state your gfx target from memory before installing anything.

Pick the runtime before the model

Four routes exist. A ROCm source fork of the upstream repository targets Linux. A patched ComfyUI stack also targets Linux and has the most detailed public bug list. A Windows ComfyUI effort is under active testing. A native C++ reimplementation ships prebuilt ROCm and Vulkan binaries for both Linux and Windows with no Python runtime at all.

Match memory to a weight format

The native runtime documents roughly 16.5 GB for its f16 set, 9.5–10 GB for Q8, and 6 GB for Q4 before working memory. Smaller sets increase the chance that a workflow fits, but the result still depends on resolution, backend, texture settings, and live buffers; the smallest route also carries the largest stated quality risk.

You have measured the complete shape and texture workflow rather than inferring support from stored weights.

Validate with the smallest run

Use a supplied sample image at the lowest practical resolution and confirm both the shape stage and the textured export before touching settings. On AMD this matters more than on NVIDIA, because several reported failures appear only in the texture stage.

A GLB opens in an independent viewer and contains the expected material channels.

Record the working combination

Write down card, gfx target, OS, ROCm version, PyTorch build, runtime commit and weight format together. AMD routes here break by version pairing far more often than by any single component being wrong.

Known trade-offs

  • Neither AMD nor Microsoft lists TRELLIS.2 as a supported workload; every route on this page is third-party work
  • AMD's own documentation states that only PyTorch is currently available on Windows and the rest of the ROCm stack remains Linux only
  • The Windows ComfyUI effort is explicitly work in progress and its maintainer warns of silent bugs that can change output without raising an error
  • A card marked expected rather than tested shares an instruction set with a tested card; that is an inference, not a report
  • Weight file size is not peak VRAM — the texture stage and working buffers sit on top

Sources