AMD GPU INDEX
Evidence, not marketing.
3 of 10 listed cards have a named project reporting an end-to-end TRELLIS.2 run. The rest are inferred or untested, and are labelled that way.
The most-reported AMD card for TRELLIS.2 right now
Same ISA and same memory as the XT
The cheapest RDNA 4 card with a usable frame buffer
The only AMD card that meets the documented 24 GB baseline
Same compile target as the XTX, four gigabytes less room
Navi 32 with enough memory for quantized runs
Quantization is not optional here
Plenty of memory, modest compute
Enormous addressable memory, integrated-GPU throughput
RDNA 2 is the gap in the current picture
Every card page reads from the same table. A cell says how much evidence exists for that combination — it does not promise the run will finish on your machine.
| GPU | VRAM | ISA | ROCm forkLinux | ComfyUI LinuxLinux | ComfyUI WindowsWindows 11 | trellis.cpp ROCmLinux · Windows | trellis.cpp VulkanLinux · Windows |
|---|---|---|---|---|---|---|---|
| RDNA 4 gfx1200 · gfx1201 | |||||||
| RX 9070 XT | 16 GB | gfx1201 | ●Tested | ○Expected | ◐Reported | ○Expected | ○Expected |
| RX 9070 | 16 GB | gfx1201 | ○Expected | ○Expected | ○Expected | ○Expected | ○Expected |
| RX 9060 XT | 16 GB | gfx1200 | ○Expected | –Unknown | –Unknown | ○Expected | ○Expected |
| RDNA 3 gfx1100 · gfx1101 · gfx1102 | |||||||
| RX 7900 XTX | 24 GB | gfx1100 | ○Expected | ●Tested | –Unknown | ○Expected | ○Expected |
| RX 7900 XT | 20 GB | gfx1100 | ○Expected | ○Expected | –Unknown | ○Expected | ○Expected |
| RX 7800 XT | 16 GB | gfx1101 | ○Expected | ○Expected | –Unknown | ○Expected | ○Expected |
| RX 7700 XT | 12 GB | gfx1101 | –Unknown | ○Expected | –Unknown | ○Expected | ○Expected |
| RX 7600 XT | 16 GB | gfx1102 | –Unknown | ○Expected | –Unknown | ○Expected | ○Expected |
| RDNA 3.5 gfx1150 · gfx1151 | |||||||
| Ryzen AI Max+ 395 | 96 GB | gfx1151 | –Unknown | ◐Reported | ◐Reported | ○Expected | ●Tested |
| RDNA 2 gfx1030 · gfx1031 · gfx1032 | |||||||
| RX 6900 XT | 16 GB | gfx1030 | –Unknown | –Unknown | ×Blocked | –Unknown | ○Expected |
A named project or maintainer reports this exact card completing the pipeline end to end.
Community reports exist but come from work in progress, partial runs, or a single tester.
Inferred from a shared instruction set with a tested card. No direct report yet.
A known dependency, kernel, or runtime gap prevents this path today.
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.
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.
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.
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.
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.
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.
| Weight format | Weights on disk | Practical VRAM | Quality note | Where it comes from |
|---|---|---|---|---|
| f16 / bf16 (default) | ≈ 16.5 GB | 24 GB comfortable | Reference output. Everything else is measured against this. | trellis.cpp default; safetensors in the ComfyUI and source routes. |
| Q8 | ≈ 9.5 GB | 16 GB practical | Described by the project as visually near-lossless. | trellis.cpp v0.5.4 and later. |
| Q4 | ≈ 6 GB | 12 GB practical, 8 GB tight | Slight 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 GB | 8 GB reported workable | Loader-dependent. Compatibility follows the custom node, not the file name. | ComfyUI GGUF loaders in the ROCm install guide. |