HunyuanVideo 1.5 VRAM requirements
Tencent's 8.3B video model from late 2025, much lighter than the original 13B HunyuanVideo. The FP8 file is the cfg-distilled variant.
TypeVideo
Parameters8.3B
Fits entirely from10 GB
8-bit or better from13 GB
01Measured on my RTX 5060 Ti 16 GB
FP8 · 848×480
11min / clip
hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors
Peak VRAM14.3 GB
System RAM peak25.2 GB
02The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 16.7 GB | 21.0 GB | 21 GB | the original weights | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| Q8_0 | 9.0 GB | 13.3 GB | 14 GB | practically identical to the original | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| FP8 | 8.3 GB | 12.6 GB | 13 GB | practically identical to the original | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| Q6_K | 7.0 GB | 11.3 GB | 12 GB | very close to the original | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| Q5_K_M | 6.1 GB | 10.4 GB | 11 GB | close; small differences in fine detail | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| Q4_K_M | 5.1 GB | 9.4 GB | 10 GB | good; some loss in fine detail and text | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
“Needed” = file + 3.5 GB working memory + 0.8 GB system reserve.
Free ComfyUI workflow, tested on my RTX 5060 Ti: 480p text to video, FP8 workflow (.json). Drag the file into ComfyUI. All workflows →
03By amount of VRAM
04Best GPU for HunyuanVideo 1.5
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for HunyuanVideo 1.5 → Planning bigger images or longer clips? Open the calculator →
05By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| Arc B570 10 GB | 10 GB | Runs | Q4_K_M | 9.4 GB |
| RTX 3080 10 GB | 10 GB | Runs | Q4_K_M | 9.4 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs | Q5_K_M | 10.4 GB |
| Arc B580 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 2060 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 3060 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 3080 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 4070 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 5070 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RX 7700 XT 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| Arc A770 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 4080 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 5080 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RX 9070 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 13.3 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| RTX 3090 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| RTX 4090 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 21.0 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 21.0 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q4_K_M | 9.4 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RX 7800M 12 GB | 12 GB | Runs | Q6_K | 11.3 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | FP8 | 12.6 GB |
| RX 7900M 16 GB | 16 GB | Runs well | Q8_0 | 13.3 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | 16-bit | 21.0 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 21.0 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 21.0 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs | Q6_K | 11.3 GB |
| Mac 18 GB | 14.4 GB | Runs well | Q8_0 | 13.3 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 13.3 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 21.0 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 21.0 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 21.0 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 21.0 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 21.0 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 21.0 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 21.0 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 21.0 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 21.0 GB |
06Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| Qwen2.5-VL 7B FP8 (scaled) qwen_2.5_vl_7b_fp8_scaled.safetensors | models/text_encoders | 9.4 GB | text encoder · smaller, recommended | Download → |
| Qwen2.5-VL 7B BF16 qwen_2.5_vl_7b.safetensors | models/text_encoders | 16.6 GB | text encoder · alternative | Download → |
| ByT5 small GlyphXL FP16 byt5_small_glyphxl_fp16.safetensors | models/text_encoders | 0.4 GB | required | Download → |
| HunyuanVideo 1.5 VAE FP16 hunyuanvideo15_vae_fp16.safetensors | models/vae | 2.5 GB | required | Download → |
| SigCLIP vision patch14 384 sigclip_vision_patch14_384.safetensors | models/clip_vision | 0.9 GB | optional · I2V only | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
07Where 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 |
08Measured and reported results
| Label | GPU | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|---|
| measured | RTX 5060 Ti 16 GB | hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors · 848x480 · 20 steps 480p text-to-video, cfg-distilled model: 121 frames (5 s at 24 fps), 20 steps, CFG 1, euler/simple, ModelSamplingSD3 shift 5, VAE Decode (Tiled). Text encoders Qwen2.5-VL 7B FP8 (s | 662.9 s / clip (121 frames) | 14.3 GB | 2026-10-12 | |
| reported | RTX 4090 24 GB | 720p model · 848x480 “The 5 seconds video took 297s to generate so barely longer than on your end” Replicated the 5090 poster's ComfyUI workflow (720p model at 848x480, 5 s @24fps); card undervolted (~5% slower per poster) | 297 s / clip | — | 2025-12-05 | huggingface.co → |
| reported | RTX 5090 32 GB | 720p model · 848x480 “I was able to generate 5 seconds video in 284s at 24fps using the 720p model at 848*480” ComfyUI; 5 s video at 24 fps; steps not stated | 284 s / clip | — | 2025-11-22 | huggingface.co → |
Other people's numbers are copied as published, with a link. Send yours.
09Training a LoRA for HunyuanVideo 1.5
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| SimpleTuner | 24 GB | stated minimum | Rank-16 LoRA, full gradient checkpointing, 480p; 720p or larger batches: 48-80GB “Minimum: 24GB-32GB VRAM is comfortable for a Rank-16 LoRA with full gradient checkpointing at 480p.” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
10Every file tracked for HunyuanVideo 1.5
| File | Type | Size | Repo |
|---|---|---|---|
| hunyuanvideo1.5_480p_t2v_cfg_distilled_fp16.safetensors (480p_t2v_cfg_distilled) | F16 | 16.65 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_720p_t2v_fp16.safetensors (720p_t2v) | F16 | 16.65 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_480p_t2v_fp16.safetensors (480p_t2v) | F16 | 16.65 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_720p_i2v_fp16.safetensors (720p_i2v) | F16 | 16.65 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors (480p_t2v_cfg_distilled) | FP8 | 8.33 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_720p_i2v_cfg_distilled_fp8_scaled.safetensors (720p_i2v_cfg_distilled) | FP8 | 8.33 GB | Comfy-Org/HunyuanVideo_1.5_repackaged → |
| hunyuanvideo1.5_720p_t2v-Q8_0.gguf | Q8_0 | 9.00 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| hunyuanvideo1.5_720p_t2v-Q6_K.gguf | Q6_K | 7.02 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| hunyuanvideo1.5_720p_t2v-Q5_K_M.gguf | Q5_K_M | 6.12 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| hunyuanvideo1.5_720p_t2v-Q5_K_S.gguf | Q5_K_S | 5.94 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| hunyuanvideo1.5_720p_t2v-Q4_K_M.gguf | Q4_K_M | 5.09 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
| hunyuanvideo1.5_720p_t2v-Q4_K_S.gguf | Q4_K_S | 4.92 GB | jayn7/HunyuanVideo-1.5_T2V_720p-GGUF → |
EXTRA (Nov 2025; Comfy-Org repo ~600k downloads). 8.3B DiT. There is no Comfy-Org fp8 of the plain (non-distilled) 720p T2V; fp8_scaled exists for cfg-distilled variants. Also 1080p super-resolution models (hunyuanvideo1.5_1080p_sr_distilled fp16 16662949080 / fp8_scaled 8335262258).