Can the RTX 5090 32 GB run MiniMax H3 Pruned?
Yes. FP8 fits on the RTX 5090 32 GB with 5.2 GB to spare.
Take FP8 (21.0 GB). In use it comes to about 26.8 GB, with 5.2 GB left over on 32 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | minimax_h3_fl2va_pruned_fp8_scaled.safetensors FP8 · Comfy-Org/MiniMax-H3 | models/diffusion_models | 21.0 GB | Download → |
| Text encoder | qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors Qwen3-VL 32B NVFP4 (AWQ) · Comfy-Org/MiniMax-H3 | models/text_encoders | 15.7 GB | Download → |
| VAE | minimax_h3_video_vae_fp16.safetensors MiniMax H3 video VAE FP16 · Comfy-Org/MiniMax-H3 | models/vae | 5.2 GB | Download → |
| Also needed | minimax_h3_audio_vae_fp32.safetensors MiniMax H3 audio VAE FP32 · Comfy-Org/MiniMax-H3 | models/vae | 0.6 GB | Download → |
| Total download · keep about the same free on disk | 42.5 GB | |||
Alternatives: Qwen3-VL 32B INT8 (convrot) (27.1 GB); Qwen3-VL 32B BF16 (51.5 GB). Sizes from Hugging Face, 2026-10-01.
System RAM: 64 GB or more. These files take about 42.5 GB of RAM while loaded, 48.5 GB with Windows and ComfyUI. What happens with less. calculated
02Every MiniMax H3 Pruned file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.2 GB | 46.0 GB | 14.0 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 21.0 GB | 26.8 GB | fits · 5.2 GB spare | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 21.0 GB | 26.8 GB | fits · 5.2 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · Abiray | 21.6 GB | 27.4 GB | fits · 4.6 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · Abiray | 16.7 GB | 22.5 GB | fits · 9.5 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · Abiray | 14.1 GB | 19.9 GB | fits · 12.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · Abiray | 11.6 GB | 17.4 GB | fits · 14.6 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · Abiray | 8.9 GB | 14.7 GB | fits · 17.3 GB spare | noticeable loss of detail | Hugging Face → |
“Needed” adds 5 GB of working memory for MiniMax H3 Pruned and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
| Label | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|
| reported | minimax_h3_fl2va_pruned_nvfp4 · 864x480 · 10 steps “175 s for a 864×480 ten-second clip, 26,914 MiB peak VRAM.” ComfyUI 0.30.1, 500 W power cap; 26,914 MiB = 26.28 GiB; INT8-ConvRot = 185 s / 28,581 MiB | 175 s / clip (243 frames) | 26.28 GB | 2026-08-04 | ai-muninn.com → |
Other people's numbers are copied as published, with a link. Send yours.
04About the RTX 5090 32 GB
The RTX 5090 32 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
32 GB GDDR7 · 512-bit · 1792 GB/s · Blackwell. Everything that runs on it →
05Questions
How much VRAM does MiniMax H3 Pruned need?
Around 14.7 GB with the smallest file (Q3_K_M) and 26.8 GB with an 8-bit file (FP8). The full 16-bit file needs about 46.0 GB.
Which MiniMax H3 Pruned file should I download for the RTX 5090 32 GB?
FP8 (21.0 GB) from Comfy-Org/MiniMax-H3.
FP8 or Q8_0 for MiniMax H3 Pruned on the RTX 5090 32 GB?
FP8 (21.0 GB): the RTX 5090 32 GB computes it natively, while Q8_0 (21.6 GB) is unpacked on the fly.
How much do I need to download for MiniMax H3 Pruned on the RTX 5090 32 GB?
42.5 GB: minimax_h3_fl2va_pruned_fp8_scaled.safetensors, qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors, minimax_h3_video_vae_fp16.safetensors, minimax_h3_audio_vae_fp32.safetensors.