HunyuanVideo (13B, original) VRAM requirements
The original 13B HunyuanVideo from December 2024. Largely replaced by the lighter HunyuanVideo 1.5, but still widely used with its LoRAs.
TypeVideo
Parameters13B
Fits entirely from11 GB
8-bit or better from18 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 25.6 GB | 29.9 GB | 30 GB | the original weights | Comfy-Org/HunyuanVideo_repackaged → |
| Q8_0 | 14.0 GB | 18.3 GB | 19 GB | practically identical to the original | city96/HunyuanVideo-gguf → |
| FP8 | 13.2 GB | 17.5 GB | 18 GB | practically identical to the original | Kijai/HunyuanVideo_comfy → |
| Q6_K | 11.0 GB | 15.3 GB | 16 GB | very close to the original | city96/HunyuanVideo-gguf → |
| Q5_K_M | 9.4 GB | 13.7 GB | 14 GB | close; small differences in fine detail | city96/HunyuanVideo-gguf → |
| Q4_K_M | 7.9 GB | 12.2 GB | 13 GB | good; some loss in fine detail and text | city96/HunyuanVideo-gguf → |
| Q3_K_M | 6.2 GB | 10.5 GB | 11 GB | noticeable loss of detail | city96/HunyuanVideo-gguf → |
“Needed” = file + 3.5 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for HunyuanVideo 13B
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for HunyuanVideo 13B → Planning bigger images or longer clips? Open the calculator →
04By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| Arc B570 10 GB | 10 GB | Offload only | Q3_K_M | 10.5 GB |
| RTX 3080 10 GB | 10 GB | Offload only | Q3_K_M | 10.5 GB |
| RTX 2080 Ti 11 GB | 11 GB | Tight | Q3_K_M | 10.5 GB |
| Arc B580 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 2060 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 3060 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 3080 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 3080 Ti 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 4070 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 4070 Super 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 4070 Ti 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 5070 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RX 7700 XT 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RX 9070 GRE 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| Arc A770 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 4080 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 5080 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 7600 XT 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 7800 XT 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 9060 XT 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 9070 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 9070 XT 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 18.3 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 3090 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 4090 24 GB | 24 GB | Runs well | FP8 | 17.5 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 29.9 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 29.9 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q4_K_M | 12.2 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RX 7800M 12 GB | 12 GB | Tight | Q3_K_M | 10.5 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RX 7900M 16 GB | 16 GB | Runs | Q6_K | 15.3 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | FP8 | 17.5 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 29.9 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 29.9 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs | Q4_K_M | 12.2 GB |
| Mac 18 GB | 14.4 GB | Runs | Q5_K_M | 13.7 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 18.3 GB |
| Mac 32 GB | 26.8 GB | Runs well | Q8_0 | 18.3 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 29.9 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 29.9 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 29.9 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 29.9 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 29.9 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 29.9 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 29.9 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 29.9 GB |
05Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| LLaVA-Llama3 FP8 (scaled) llava_llama3_fp8_scaled.safetensors | models/text_encoders | 9.1 GB | text encoder · smaller, recommended | Download → |
| LLaVA-Llama3 FP16 llava_llama3_fp16.safetensors | models/text_encoders | 16.1 GB | text encoder · alternative | Download → |
| CLIP-L clip_l.safetensors | models/text_encoders | 0.2 GB | required | Download → |
| HunyuanVideo VAE BF16 hunyuan_video_vae_bf16.safetensors | models/vae | 0.5 GB | required | Download → |
| LLaVA-Llama3 vision llava_llama3_vision.safetensors | models/clip_vision | 0.6 GB | optional · I2V only | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
06Where the files go in ComfyUI
| File | Folder | Loader node |
|---|---|---|
| Diffusion model (.safetensors: 16-bit, FP8, INT8) | ComfyUI/models/diffusion_models | Load Diffusion Model |
| GGUF file (.gguf) | ComfyUI/models/unet | Unet Loader (GGUF) - from the ComfyUI-GGUF node pack |
| Text encoder | ComfyUI/models/text_encoders | Load CLIP / DualCLIPLoader (or the GGUF versions) |
| VAE | ComfyUI/models/vae | Load VAE |
07Measured and reported results
No measured results yet. Send yours.
08Training a LoRA for HunyuanVideo 13B
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| musubi-tuner | 24 GB | stated minimum | Without --fp8_base (bf16 DiT); use --blocks_to_swap as needed; fp8_base lowers this but no figure given “If --fp8_base is not specified, 24GB or more VRAM is recommended.” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
09Every file tracked for HunyuanVideo 13B
| File | Type | Size | Repo |
|---|---|---|---|
| hunyuan_video_t2v_720p_bf16.safetensors | BF16 | 25.64 GB | Comfy-Org/HunyuanVideo_repackaged → |
| hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors | FP8 | 13.19 GB | Kijai/HunyuanVideo_comfy → |
| hunyuan-video-t2v-720p-BF16.gguf | BF16 | 25.65 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q8_0.gguf | Q8_0 | 13.97 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q6_K.gguf | Q6_K | 10.95 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q5_1.gguf | Q5_1 | 10.08 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q5_K_M.gguf | Q5_K_M | 9.45 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q5_0.gguf | Q5_0 | 9.30 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q5_K_S.gguf | Q5_K_S | 9.30 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q4_1.gguf | Q4_1 | 8.52 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q4_K_M.gguf | Q4_K_M | 7.88 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q4_0.gguf | Q4_0 | 7.74 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q4_K_S.gguf | Q4_K_S | 7.74 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q3_K_M.gguf | Q3_K_M | 6.24 GB | city96/HunyuanVideo-gguf → |
| hunyuan-video-t2v-720p-Q3_K_S.gguf | Q3_K_S | 6.09 GB | city96/HunyuanVideo-gguf → |
Text encoders: llava-llama-3-8B + clip_l. Superseded by HunyuanVideo 1.5 (8.3B).