Wan 2.1 T2V 14B VRAM requirements
Alibaba's 14B text-to-video model. Figures assume a short clip at 480p; higher resolution and more frames need more memory.
TypeVideo
Parameters14B
Fits entirely from12 GB
8-bit or better from19 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 28.6 GB | 32.9 GB | 33 GB | the original weights | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| Q8_0 | 15.9 GB | 20.2 GB | 21 GB | practically identical to the original | city96/Wan2.1-T2V-14B-gguf → |
| FP8 | 14.3 GB | 18.6 GB | 19 GB | practically identical to the original | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| Q6_K | 12.5 GB | 16.8 GB | 17 GB | very close to the original | city96/Wan2.1-T2V-14B-gguf → |
| Q5_K_M | 11.3 GB | 15.6 GB | 16 GB | close; small differences in fine detail | city96/Wan2.1-T2V-14B-gguf → |
| Q4_K_M | 10.1 GB | 14.4 GB | 15 GB | good; some loss in fine detail and text | city96/Wan2.1-T2V-14B-gguf → |
| Q3_K_M | 7.6 GB | 11.9 GB | 12 GB | noticeable loss of detail | city96/Wan2.1-T2V-14B-gguf → |
“Needed” = file + 3.5 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for Wan 2.1 14B
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Wan 2.1 14B → 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 | 14.4 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| Arc B570 10 GB | 10 GB | Offload only | Q3_K_M | 11.9 GB |
| RTX 3080 10 GB | 10 GB | Offload only | Q3_K_M | 11.9 GB |
| RTX 2080 Ti 11 GB | 11 GB | Offload only | Q3_K_M | 11.9 GB |
| Arc B580 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 2060 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 3060 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 3080 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 3080 Ti 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 4070 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 4070 Super 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 4070 Ti 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 5070 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RX 7700 XT 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RX 9070 GRE 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| Arc A770 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 4080 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 5080 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 7600 XT 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 7800 XT 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 9060 XT 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 9070 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 9070 XT 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | FP8 | 18.6 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | Q8_0 | 20.2 GB |
| RTX 3090 24 GB | 24 GB | Runs well | Q8_0 | 20.2 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | Q8_0 | 20.2 GB |
| RTX 4090 24 GB | 24 GB | Runs well | FP8 | 18.6 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | Q8_0 | 20.2 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | Q8_0 | 20.2 GB |
| RTX 5090 32 GB | 32 GB | Runs well | FP8 | 18.6 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Not practical | Q3_K_M | 11.9 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Not practical | Q3_K_M | 11.9 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q4_K_M | 14.4 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RX 7800M 12 GB | 12 GB | Tight | Q3_K_M | 11.9 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RX 7900M 16 GB | 16 GB | Runs | Q5_K_M | 15.6 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | FP8 | 18.6 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 32.9 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 32.9 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Tight | Q3_K_M | 11.9 GB |
| Mac 18 GB | 14.4 GB | Tight | Q3_K_M | 11.9 GB |
| Mac 24 GB | 19.6 GB | Runs | Q6_K | 16.8 GB |
| Mac 32 GB | 26.8 GB | Runs well | Q8_0 | 20.2 GB |
| Mac 36 GB | 30.2 GB | Runs well | Q8_0 | 20.2 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 32.9 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 32.9 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 32.9 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 32.9 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 32.9 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 32.9 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 32.9 GB |
05Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| UMT5-XXL FP8 (scaled) umt5_xxl_fp8_e4m3fn_scaled.safetensors | models/text_encoders | 6.7 GB | text encoder · smaller, recommended | Download → |
| UMT5-XXL FP16 umt5_xxl_fp16.safetensors | models/text_encoders | 11.4 GB | text encoder · alternative | Download → |
| Wan 2.1 VAE wan_2.1_vae.safetensors | models/vae | 0.3 GB | required | 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 Wan 2.1 14B
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| diffusion-pipe | 24 GB | example run | Example config: 512x512x81 videos, fp8 transformer, blocks_to_swap 32, rank 32, AdamW8bitKahan, unsloth activation checkpointing “train Wan 14b t2v on 512x512x81 sized videos (or varying aspect ratios of the same size), with 24GB VRAM.” | github.com → |
| ai-toolkit | 24 GB | example run | Official example config: ~480p (632), 40 frames, rank 32, batch 1, quantized base + TE, low_vram, text encoder unloaded (single trigger prompt only; captions need more VRAM) “This config should work on 24GB GPUs.” | github.com → |
| SimpleTuner | 24 GB | stated minimum | 832x480; no further settings given ('fiddle with the settings') “It'll fit in 24G, but you'll have to fiddle with the settings a bit.” | github.com → |
| musubi-tuner | 24 GB | stated minimum | 720x1280 images (not video), fp8 and block swap “training with 720x1280 images with 24GB VRAM” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
09Every file tracked for Wan 2.1 14B
| File | Type | Size | Repo |
|---|---|---|---|
| wan2.1_t2v_14B_fp16.safetensors | F16 | 28.58 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| wan2.1_t2v_14B_bf16.safetensors | BF16 | 28.58 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| wan2.1_t2v_14B_fp8_scaled.safetensors | FP8 | 14.29 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| wan2.1_t2v_14B_fp8_e4m3fn.safetensors | FP8 | 14.29 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| wan2.1-t2v-14b-BF16.gguf | BF16 | 29.05 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-F16.gguf | F16 | 29.05 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q8_0.gguf | Q8_0 | 15.88 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q6_K.gguf | Q6_K | 12.48 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q5_1.gguf | Q5_1 | 11.49 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q5_K_M.gguf | Q5_K_M | 11.26 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q5_0.gguf | Q5_0 | 10.79 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q5_K_S.gguf | Q5_K_S | 10.61 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q4_K_M.gguf | Q4_K_M | 10.12 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q4_1.gguf | Q4_1 | 9.73 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q4_K_S.gguf | Q4_K_S | 9.22 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q4_0.gguf | Q4_0 | 9.03 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q3_K_M.gguf | Q3_K_M | 7.65 GB | city96/Wan2.1-T2V-14B-gguf → |
| wan2.1-t2v-14b-Q3_K_S.gguf | Q3_K_S | 6.99 GB | city96/Wan2.1-T2V-14B-gguf → |
Text encoder umt5_xxl. Activations for video latents add significant VRAM on top of weights (resolution x frames).