Wan 2.2 TI2V 5B VRAM requirements
A single dense 5B model for text- or image-to-video at 720p. The friendliest Wan for 8–12 GB cards.
TypeVideo
Parameters5B
Fits entirely from6 GB
8-bit or better from10 GB
01Measured on my RTX 5060 Ti 16 GB
16-bit · 1280×704
8.6min / clip
wan2.2_ti2v_5B_fp16.safetensors
Peak VRAM11.0 GB
Setup20 steps
02The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 10.0 GB | 13.8 GB | 14 GB | the original weights | Comfy-Org/Wan_2.2_ComfyUI_Repackaged → |
| Q8_0 | 5.4 GB | 9.2 GB | 10 GB | practically identical to the original | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Q6_K | 4.2 GB | 8.0 GB | 9 GB | very close to the original | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Q5_K_M | 3.8 GB | 7.6 GB | 8 GB | close; small differences in fine detail | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Q4_K_M | 3.4 GB | 7.2 GB | 8 GB | good; some loss in fine detail and text | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Q3_K_M | 2.5 GB | 6.3 GB | 7 GB | noticeable loss of detail | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Q2_K | 1.9 GB | 5.7 GB | 6 GB | heavy loss; a last resort | QuantStack/Wan2.2-TI2V-5B-GGUF → |
“Needed” = file + 3 GB working memory + 0.8 GB system reserve.
Free ComfyUI workflow, tested on my RTX 5060 Ti: text to video workflow (.json). Drag the file into ComfyUI. All workflows →
03By amount of VRAM
04Best GPU for Wan 2.2 5B
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Wan 2.2 5B → 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 | Tight | Q2_K | 5.7 GB |
| RTX 3050 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 2070 Super 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 2080 Super 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3050 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3060 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3060 Ti 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3070 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3070 Ti 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 4060 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 4060 Ti 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5050 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5060 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5060 Ti 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 7600 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 9050 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 9060 XT 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| Arc B570 10 GB | 10 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 3080 10 GB | 10 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs well | Q8_0 | 9.2 GB |
| Arc B580 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 2060 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 3060 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 3080 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 4070 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 5070 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RX 7700 XT 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| Arc A770 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4080 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5080 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 9070 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | 16-bit | 13.8 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| RTX 3090 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4090 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 13.8 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q2_K | 5.7 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q2_K | 5.7 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 7600M 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 7600M XT 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 7600S 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RX 7700S 8 GB | 8 GB | Runs | Q5_K_M | 7.6 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RX 7800M 12 GB | 12 GB | Runs well | Q8_0 | 9.2 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RX 7900M 16 GB | 16 GB | Runs well | 16-bit | 13.8 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | 16-bit | 13.8 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 13.8 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 13.8 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs well | Q8_0 | 9.2 GB |
| Mac 18 GB | 14.4 GB | Runs well | 16-bit | 13.8 GB |
| Mac 24 GB | 19.6 GB | Runs well | 16-bit | 13.8 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 13.8 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 13.8 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 13.8 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 13.8 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 13.8 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 13.8 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 13.8 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 13.8 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 13.8 GB |
06Text 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 2.2 VAE wan2.2_vae.safetensors | models/vae | 1.4 GB | required | 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 | wan2.2_ti2v_5B_fp16.safetensors · 1280x704 · 20 steps Text to video, 121 frames (about 5 s at 24 fps). 2 timed runs (516.2 and 514.0 s) after 1 warm-up (528.9 s incl. loading). UMT5-XXL FP8 + Wan 2.2 VAE, uni_pc/simple, CFG 5, shift 8 | 515.1 s / clip (121 frames) | 11.0 GB | 2026-09-27 | |
| reported | Arc B580 12 GB | Wan 2.2 5B T2V (template) · 640x352 “Wan 2.2 5B Text to Video (640x352, 121 frames): FAST (60s, very poor quality)” Arc B580 12GB, PyTorch 2.8 XPU; same post: 960x544/121f = 181s, 1280x704 OOM; steps not stated | 60 s / clip (121 frames) | — | 2025-08-03 | github.com → |
| reported | RTX 4060 Laptop 8 GB | Wan2_2-TI2V-5B_fp8_e4m3fn_scaled_KJ · 480x480 · 30 steps “30/30 [00:57<00:00, 1.93s/it] ... Prompt executed in 94.93 seconds” Article says "RTX 4060 (8GB VRAM)", 32 GB RAM, Win 11; same author (lilting) documents this machine as an RTX 4060 Laptop in other posts; I2V; frames not stated; 50 steps = 113.93 | 94.93 s / clip · 1.93 s/it | — | 2026-03-06 | lilting.ch → |
Other people's numbers are copied as published, with a link. Send yours.
09Training a LoRA for Wan 2.2 5B
No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →
10Every file tracked for Wan 2.2 5B
| File | Type | Size | Repo |
|---|---|---|---|
| wan2.2_ti2v_5B_fp16.safetensors | F16 | 10.00 GB | Comfy-Org/Wan_2.2_ComfyUI_Repackaged → |
| Wan2.2-TI2V-5B-Q8_0.gguf | Q8_0 | 5.40 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q6_K.gguf | Q6_K | 4.21 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q5_1.gguf | Q5_1 | 3.87 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q5_K_M.gguf | Q5_K_M | 3.81 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q5_0.gguf | Q5_0 | 3.64 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q5_K_S.gguf | Q5_K_S | 3.56 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q4_K_M.gguf | Q4_K_M | 3.43 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q4_1.gguf | Q4_1 | 3.25 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q4_K_S.gguf | Q4_K_S | 3.12 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q4_0.gguf | Q4_0 | 3.03 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q3_K_M.gguf | Q3_K_M | 2.55 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q3_K_S.gguf | Q3_K_S | 2.29 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
| Wan2.2-TI2V-5B-Q2_K.gguf | Q2_K | 1.85 GB | QuantStack/Wan2.2-TI2V-5B-GGUF → |
Single dense 5B model (text+image to video, 720p24). Uses the new Wan 2.2 VAE (not the 2.1 VAE). No FP8 from Comfy-Org.