Can the Mac 24 GB run Wan 2.2 T2V A14B?
Not at full quality. The 16-bit and 8-bit files are too big for the Mac 24 GB; the largest that fits is Q6_K (12.0 GB).
Take Q6_K (12.0 GB). In use it comes to about 16.3 GB, with 3.3 GB left over on 19.6 GB. Quality: very close to the original. For better quality, Q8_0 (15.4 GB) also runs, with about 0.1 GB spilling into system RAM - a little slower, still practical.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-T2V-A14B-HighNoise-Q6_K.gguf high-noise model (early steps) Q6_K · QuantStack/Wan2.2-T2V-A14B-GGUF | models/unet | 12.0 GB | Download → |
| Model | Wan2.2-T2V-A14B-LowNoise-Q6_K.gguf low-noise model (late steps) Q6_K · QuantStack/Wan2.2-T2V-A14B-GGUF | models/unet | 12.0 GB | Download → |
| Text encoder | umt5-xxl-encoder-Q8_0.gguf UMT5-XXL GGUF Q8_0 · city96/umt5-xxl-encoder-gguf | models/text_encoders | 6.0 GB | Download → |
| VAE | wan_2.1_vae.safetensors Wan 2.1 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 30.3 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). On a Mac, FP8 text encoders do not load, so a 16-bit one is listed - or a GGUF one, loaded with “CLIPLoader (GGUF)” from the ComfyUI-GGUF nodes. Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json) · GGUF Q5_K_M workflow (.json). Drag the file into ComfyUI. All workflows →
Shared memory: about 36.3 GB of your 24 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 12.3 GB more than there is. It still runs: while the model works, the system compresses or swaps the idle text encoder, so loading and changing the prompt get slower. A smaller file or text encoder avoids that. calculated
02Every Wan 2.2 T2V file on 19.6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 28.6 GB | 32.9 GB | 13.3 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 15.4 GB | 19.7 GB | spills 0.1 GB | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · QuantStack | 12.0 GB | 16.3 GB | fits · 3.3 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 10.8 GB | 15.1 GB | fits · 4.5 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 9.7 GB | 14.0 GB | fits · 5.6 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 7.2 GB | 11.5 GB | fits · 8.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 5.3 GB | 9.6 GB | fits · 10.0 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3.5 GB of working memory for Wan 2.2 T2V and a 0.8 GB reserve. Sizes 2026-10-01. Wan 2.2 A14B uses two files of this size (high-noise and low-noise); only one sits in VRAM at a time, both must fit in system RAM. FP8 and INT8 files are left out on a Mac: Apple GPUs cannot compute FP8, so ComfyUI either fails to load them or converts them back to 16-bit, which saves no memory. Use a 16-bit or GGUF file.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 T2V on a Mac 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 20 GB you could run Wan 2.2 T2V at 8-bit or better (Q8_0, 15.4 GB) with no offloading.
05About the Mac 24 GB
A Mac with 24 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 19.6 GB of it by default (older macOS versions: about 17.2 GB); that is the figure used here. ComfyUI can go past it, but macOS then starts compressing and swapping memory and everything slows down. ComfyUI runs on Apple GPUs through PyTorch's MPS backend. 16-bit and GGUF files work; FP8 and INT8 files do not save memory on a Mac, so they are skipped. Speed is the catch: even the fastest Macs are several times slower per image than a desktop RTX card. Chips sold with 24 GB: M2, M3, M4, M4 Pro, M5, M5 Pro, M6 (memory bandwidth 100–307 GB/s - the higher, the faster). Everything about Macs and local AI →
24 GB unified · ~19.6 GB for the GPU · 100–307 GB/s · Apple Silicon. Everything that runs on it →
06Questions
How much VRAM does Wan 2.2 T2V need?
Around 9.6 GB with the smallest file (Q2_K) and 18.6 GB with an 8-bit file (FP8). The full 16-bit file needs about 32.9 GB.
Which Wan 2.2 T2V file should I download for the Mac 24 GB?
Q6_K (12.0 GB) from QuantStack/Wan2.2-T2V-A14B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Wan 2.2 T2V on the Mac 24 GB?
Q8_0 (15.4 GB). The Mac 24 GB has no FP8 maths, so FP8 (14.3 GB) only saves memory and is a step further from the original.
How much do I need to download for Wan 2.2 T2V on the Mac 24 GB?
30.3 GB: Wan2.2-T2V-A14B-HighNoise-Q6_K.gguf, Wan2.2-T2V-A14B-LowNoise-Q6_K.gguf, umt5-xxl-encoder-Q8_0.gguf, wan_2.1_vae.safetensors.