Can the RTX 5070 12 GB run MiniMax H3 Pruned?
Not entirely. Even Q4_K_M is 5.4 GB over 12 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, Q4_K_M (11.6 GB), needs about 17.4 GB - 5.4 GB more than RTX 5070 12 GB has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
Also try the FP8 file (21.0 GB) on this GPU. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →
01With more VRAM
With 32 GB you could run MiniMax H3 Pruned at 8-bit or better (FP8, 21.0 GB) with no offloading: for example on the RTX 5090 32 GB.
What changes from the RTX 5070 12 GB to the RTX 5070 Ti 16 GB →
02Every MiniMax H3 Pruned file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.2 GB | 46.0 GB | 34.0 GB too big | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 21.0 GB | 26.8 GB | 14.8 GB too big | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 21.0 GB | 26.8 GB | 14.8 GB too big | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · Abiray | 21.6 GB | 27.4 GB | 15.4 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · Abiray | 16.7 GB | 22.5 GB | 10.5 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · Abiray | 14.1 GB | 19.9 GB | 7.9 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · Abiray | 11.6 GB | 17.4 GB | 5.4 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · Abiray | 8.9 GB | 14.7 GB | 2.7 GB too big | 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.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | MiniMax-H3-FL2VA-Pruned-Q4_K_M.gguf Q4_K_M · Abiray/MiniMax-H3-Pruned-GGUF | models/unet | 11.6 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 | 33.1 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: 48 GB or more. These files take about 33.1 GB of RAM while loaded, 39.1 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
At 15.7 GB even the smallest Qwen3-VL 32B file is too big for 12 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 51.5 GB, INT8 27.1 GB, NVFP4 15.7 GB. Why the encoder does not count against VRAM →
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run MiniMax H3 Pruned on a RTX 5070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the RTX 5070 12 GB
The RTX 5070 12 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.
12 GB GDDR7 · 192-bit · 672 GB/s · Blackwell. Everything that runs on it →
07Questions
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 5070 12 GB?
Q4_K_M (11.6 GB) from Abiray/MiniMax-H3-Pruned-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for MiniMax H3 Pruned on the RTX 5070 12 GB?
FP8 (21.0 GB): the RTX 5070 12 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 5070 12 GB?
33.1 GB: MiniMax-H3-FL2VA-Pruned-Q4_K_M.gguf, qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors, minimax_h3_video_vae_fp16.safetensors, minimax_h3_audio_vae_fp32.safetensors.