Can My GPU Run HuMo 17B?
Image to Video · VRAM requirements and compatibility for 78 GPUs
Human-centric video from text, a reference image and audio together, with lip-sync; built on Wan 2.1. HuMo 17B is a image to video model — developed by ByteDance Research, released 2025-09, 17B parameters, 34.1 GB download, license: apache-2.0.
Short answer: you need at least 7 GB of VRAM (17 GB recommended). 76 of 78 GPUs can run it; the smallest NVIDIA card that can is the GTX 1070 (8 GB).
Check HuMo 17B on your GPUHuMo 17B VRAM requirements
| Format | VRAM |
|---|---|
| FP16 (full precision) | 34 GB |
| FP8 | 17 GB |
| GGUF Q4 | 10 GB |
| GGUF Q3 | 9 GB |
| Minimum | 7 GB |
| Recommended | 17 GB |
| Optimal | 34 GB |
Tip: FP8 is 17.1 GB; a 1.7B version also exists.
Available as: ComfyUI, Diffusers, GGUF quantized versions, FP8 versions, CPU offloading.
Official pages: Hugging Face
Which GPUs can run HuMo 17B?
Ratings go from S (perfect) to F (can't run) and use the best format that fits in each card's VRAM. How ratings work.
NVIDIA
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| RTX 5090 | 32 GB | Perfect | FP8 | Fast | Details |
| RTX 5080 | 16 GB | Great | GGUF Q4 | Moderate | Details |
| RTX 5070 Ti | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 5070 | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 5060 Ti 16GB | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 5060 Ti 8GB | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 5060 | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 4090 | 24 GB | Great | FP8 | Fast | Details |
| RTX 4080 Super | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4080 | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4070 Ti Super | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4070 Ti | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4070 Super | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4070 | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 4060 Ti 16GB | 16 GB | Good | GGUF Q4 | Slow | Details |
| RTX 4060 Ti 8GB | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 4060 | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 3090 Ti | 24 GB | Great | GGUF Q4 | Moderate | Details |
| RTX 3090 | 24 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3080 Ti | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3080 12GB | 12 GB | Good | GGUF Q4 | Moderate | Details |
| RTX 3080 10GB | 10 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 3070 Ti | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 3070 | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 3060 Ti | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 5050 | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 3060 | 12 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2080 Ti | 11 GB | Usable | GGUF Q4 | Slow | Details |
| RTX 2080 Super | 8 GB | Usable | Offload | Very Slow | Details |
| RTX 2080 | 8 GB | Barely | Offload | Very Slow | Details |
| RTX 2070 Super | 8 GB | Barely | Offload | Very Slow | Details |
| RTX 2070 | 8 GB | Barely | Offload | Very Slow | Details |
| RTX 2060 Super | 8 GB | Barely | Offload | Very Slow | Details |
| RTX 2060 | 6 GB | Can't Run | — | — | Details |
| GTX 1080 Ti | 11 GB | Usable | GGUF Q4 | Slow | Details |
| GTX 1080 | 8 GB | Barely | Offload | Very Slow | Details |
| GTX 1070 Ti | 8 GB | Barely | Offload | Very Slow | Details |
| GTX 1070 | 8 GB | Barely | Offload | Very Slow | Details |
| GTX 1060 6GB | 6 GB | Can't Run | — | — | Details |
AMD
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| RX 9070 XT | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 9070 | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 7900 XTX | 24 GB | Good | GGUF Q4 | Moderate | Details |
| RX 9070 GRE | 12 GB | Good | GGUF Q4 | Slow | Details |
| RX 7900 XT | 20 GB | Good | GGUF Q4 | Moderate | Details |
| RX 9060 XT 16GB | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 9060 XT 8GB | 8 GB | Usable | Offload | Very Slow | Details |
| RX 7900 GRE | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 7800 XT | 16 GB | Good | GGUF Q4 | Moderate | Details |
| RX 7700 XT | 12 GB | Usable | GGUF Q4 | Slow | Details |
| RX 7600 XT | 16 GB | Usable | GGUF Q4 | Slow | Details |
| RX 7600 | 8 GB | Barely | Offload | Very Slow | Details |
| RX 6950 XT | 16 GB | Good | GGUF Q4 | Slow | Details |
| RX 6900 XT | 16 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6800 XT | 16 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6800 | 16 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6700 XT | 12 GB | Usable | GGUF Q4 | Slow | Details |
| RX 6600 XT | 8 GB | Barely | Offload | Very Slow | Details |
| RX 6600 | 8 GB | Barely | Offload | Very Slow | Details |
Apple
| GPU | VRAM | Rating | Runs as | Speed | |
|---|---|---|---|---|---|
| M5 Ultra | 96 GB | Usable | FP16 | Fast | Details |
| M3 Ultra | 96 GB | Usable | FP16 | Fast | Details |
| M4 Max | 48 GB | Barely | FP16 | Moderate | Details |
| M5 Max | 48 GB | Barely | FP16 | Moderate | Details |
| M4 Pro | 24 GB | Barely | GGUF Q4 | Slow | Details |
| M5 Pro | 24 GB | Barely | GGUF Q4 | Slow | Details |
| M4 | 16 GB | Can't Run | GGUF Q4 | Slow | Details |
| M3 Max | 36 GB | Barely | FP16 | Moderate | Details |
| M3 Pro | 18 GB | Barely | GGUF Q4 | Slow | Details |
| M5 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M6 | 16 GB | Barely | GGUF Q4 | Slow | Details |
| M3 | 16 GB | Can't Run | GGUF Q4 | Slow | Details |
| M2 Ultra | 192 GB | Usable | FP16 | Fast | Details |
| M2 Max | 96 GB | Usable | FP16 | Moderate | Details |
| M2 Pro | 32 GB | Barely | GGUF Q4 | Slow | Details |
| M2 | 24 GB | Barely | GGUF Q4 | Slow | Details |
| M1 Ultra | 128 GB | Usable | FP16 | Fast | Details |
| M1 Max | 64 GB | Barely | FP16 | Moderate | Details |
| M1 Pro | 32 GB | Barely | GGUF Q4 | Slow | Details |
| M1 | 16 GB | Can't Run | GGUF Q4 | Slow | Details |
Frequently asked questions
How much VRAM does HuMo 17B need?
HuMo 17B needs at least 7 GB of VRAM, 17 GB recommended, and 34 GB to run at full FP16 precision.
Can HuMo 17B run on 8 GB of VRAM (e.g. NVIDIA RTX 4060)?
On the NVIDIA RTX 4060: yes, with CPU offloading (rating C, usable).
Can HuMo 17B run on the NVIDIA RTX 3060 (12 GB)?
Yes, in GGUF Q4 (rating C, usable).
Which GPUs can run HuMo 17B?
76 of the 78 GPUs we track can run it, and 26 run it well (rating B or better). The cheapest one that runs it well is the AMD RX 9060 XT 16GB (16 GB, about $349).
Does HuMo 17B work on AMD or Apple Silicon?
19 AMD Radeon and 20 Apple Silicon chips in our list can run it. There is no MPS backend, so it may not work on Apple Silicon.