**MiniMax H3 produces pure noise/mosaic on AMD RX 7900 XTX (RDNA3/gfx1100) with official template — all quantization/backend combos affected**
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Environment
- GPU: AMD Radeon RX 7900 XTX (gfx1100, RDNA3), 24GB VRAM
- RAM: 32GB + 106GB swap
- OS: Ubuntu 24.04, ROCm 7.2.4
- PyTorch: 2.13.0+rocm7.2
- ComfyUI: master @ 1868372d, comfy-kitchen 0.2.26, comfy-aimdo 0.4.11
- Launch args: `--disable-pinned-memory --enable-dynamic-vram --fast-disk --vram-headroom 3 --async-offload` (+ `ROCR_VISIBLE_DEVICES=0` to hide iGPU)
### Symptom
MiniMax H3 official T2V template (and every variant tried) generates pure noise / mosaic ("snow"). Video VAE zero-latent test decodes fine (smooth grey), model files verify complete (DiT 932 keys, TE 2054 keys), GPU runs at 100% + 92°C (it computes, but produces garbage). Different seeds give different noise (not fixed corruption).
### Verified / excluded (all still noise)
- TE: nvfp4_awq AND int8_convrot (both native & emulated quant paths)
- Sampler: res_multistep AND euler
- Resolution: 640x352 / 832x480 / 1344x768
- Backend: HIP (comfy-kitchen) AND eager-only (pure PyTorch)
- Memory: swap increased 56G→106G (rules out OOM for T2V)
- Attention: applied `low_precision_attention=False` to H3 DiT (issue #15263 fix) — still noise
- Model files: safetensors integrity OK
### Additional data
- I2V (first_frame) path: ComfyUI SIGABRT crash, /var/crash report VmPeak=66.9GB (separate OOM issue)
- HIP backend registers correctly: `registered HIP backend for gfx1100 (with WMMA)`
- Native ops: int8_tensorwise, convrot_w4a4 | emulated: nvfp4, fp8, mxfp8
### Hypothesis
RDNA3 (gfx1100) specific operator issue in the quantized DiT forward (convrot_w4a4 / int8 attention path). A user on AMD RX 7800 XT (RDNA4) + Windows ROCm 7.14 reports video generation works fine (#15283), suggesting newer ROCm / RDNA4 fixes it, while RDNA3 on ROCm 7.2.4 does not.
### Files used (official)
- minimax_h3_fl2va_pruned_int8_convrot.safetensors (21G)
- qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors (15.7G)
- minimax_h3_video_vae_fp16 / minimax_h3_audio_vae_fp32
Contributor guide
Research direction
Start by reproducing the official MiniMax H3 T2V template on the listed RX 7900 XTX environment, comparing the HIP and eager-only paths. Inspect the quantized DiT forward, especially the convrot_w4a4 and int8 attention paths named in the hypothesis; done means H3 produces valid video rather than noise on gfx1100 without breaking the tested quantization and sampler combinations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- linux, python, pytorch, ubuntu
- Domain
- ai, backend, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100