Wan 2.1 T2V 1.3B VRAM requirements
The small Wan: 1.3B parameters, 2.8 GB at full precision. Its text encoder is four times bigger than the model itself.
TypeVideo
Parameters1.3B
Fits entirely from4 GB
8-bit or better from5 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 2.8 GB | 5.6 GB | 6 GB | the original weights | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| Q8_0 | 1.5 GB | 4.3 GB | 5 GB | practically identical to the original | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Q6_K | 1.2 GB | 4.0 GB | 4 GB | very close to the original | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Q5_K_M | 1.1 GB | 3.9 GB | 4 GB | close; small differences in fine detail | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Q4_K_M | 1.0 GB | 3.8 GB | 4 GB | good; some loss in fine detail and text | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Q3_K_M | 0.7 GB | 3.5 GB | 4 GB | noticeable loss of detail | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
“Needed” = file + 2 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for Wan 2.1 1.3B
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Wan 2.1 1.3B → 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 | Runs well | 16-bit | 5.6 GB |
| RTX 3050 6 GB | 6 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2070 Super 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2080 Super 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3050 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3060 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3060 Ti 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3070 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3070 Ti 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4060 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4060 Ti 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5050 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5060 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5060 Ti 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 7600 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 9050 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 9060 XT 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| Arc B570 10 GB | 10 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 10 GB | 10 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs well | 16-bit | 5.6 GB |
| Arc B580 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2060 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3060 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4070 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5070 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RX 7700 XT 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| Arc A770 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4080 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5080 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 9070 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | 16-bit | 5.6 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3090 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4090 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 5.6 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Runs | Q6_K | 4.0 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Runs | Q6_K | 4.0 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 7600M 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 7600M XT 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 7600S 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RX 7700S 8 GB | 8 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RX 7800M 12 GB | 12 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RX 7900M 16 GB | 16 GB | Runs well | 16-bit | 5.6 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | 16-bit | 5.6 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 5.6 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 5.6 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs well | 16-bit | 5.6 GB |
| Mac 18 GB | 14.4 GB | Runs well | 16-bit | 5.6 GB |
| Mac 24 GB | 19.6 GB | Runs well | 16-bit | 5.6 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 5.6 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 5.6 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 5.6 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 5.6 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 5.6 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 5.6 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 5.6 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 5.6 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 5.6 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 1.3B
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| SimpleTuner | 12 GB | example run | 832x480, rank-16 LoRA, batch size 4 (measured figure, 'a bit more than 12G') “Rank-16 LoRA uses a bit more than 12G (batch size 4)” | github.com → |
| ai-toolkit | 24 GB | example run | Official example config named for 24GB: ~480p (632), 40 frames, rank 32, batch 1, quantized TE; filename is the only VRAM figure “train_lora_wan21_1b_24gb.yaml” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
09Every file tracked for Wan 2.1 1.3B
| File | Type | Size | Repo |
|---|---|---|---|
| wan2.1_t2v_1.3B_fp16.safetensors | F16 | 2.84 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| wan2.1_t2v_1.3B_bf16.safetensors | BF16 | 2.84 GB | Comfy-Org/Wan_2.1_ComfyUI_repackaged → |
| Wan2.1-T2V-1.3B-F16.gguf | F16 | 2.84 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q8_0.gguf | Q8_0 | 1.54 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q6_K.gguf | Q6_K | 1.20 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q5_1.gguf | Q5_1 | 1.10 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q5_K_M.gguf | Q5_K_M | 1.09 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q5_0.gguf | Q5_0 | 1.04 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q5_K_S.gguf | Q5_K_S | 1.01 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q4_K_M.gguf | Q4_K_M | 0.98 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q4_1.gguf | Q4_1 | 0.93 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q4_K_S.gguf | Q4_K_S | 0.89 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q4_0.gguf | Q4_0 | 0.87 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q3_K_M.gguf | Q3_K_M | 0.73 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
| Wan2.1-T2V-1.3B-Q3_K_S.gguf | Q3_K_S | 0.65 GB | samuelchristlie/Wan2.1-T2V-1.3B-GGUF → |
No city96 GGUF (city96/Wan2.1-T2V-1.3B-gguf returns 401). samuelchristlie is the most-downloaded GGUF. Model is small enough that GGUF rarely matters; the umt5 text encoder (11.4GB fp16) is larger than the model.