Can the Mac 48 GB run LTX-2.5 (22B)?
Yes. Q8_0 fits on the Mac 48 GB with 11.8 GB to spare.
Q8_0 (23.6 GB) needs about 28.4 GB in use, so 11.8 GB of the 40.2 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | LTX-2.5-Distilled-Q8_0.gguf Q8_0 · realrebelai/LTX-2.5_GGUFs | models/unet | 23.6 GB | Download → |
| Text encoder | gemma4-12b-with-proj-ltx-2.5-bf16.safetensors Gemma 4 12B + LTX projection BF16 · Lightricks/LTX-2.5 | models/text_encoders | 26.3 GB | Download → |
| VAE | ltx-2.5-video-vae-bf16.safetensors LTX-2.5 video VAE (DiffVAE) BF16 · Lightricks/LTX-2.5 | models/vae | 1.5 GB | Download → |
| Also needed | ltx-2.5-audio-vae-bf16.safetensors LTX-2.5 audio VAE + vocoder BF16 · Lightricks/LTX-2.5 | models/vae | 0.4 GB | Download → |
| Total download · keep about the same free on disk | 51.7 GB | |||
Only for some workflows: LTX-2.5 latent spatial upscaler x2 (1.0 GB, official two-stage template); Gemma 4 E2B INT8 (prompt enhancer, optional) (5.2 GB, only if prompt enhancer enabled). On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. Sizes from Hugging Face, 2026-10-01.
Shared memory: about 57.7 GB of your 48 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 9.7 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 LTX-2.5 file on 40.2 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Lightricks | 42.0 GB | 46.8 GB | 6.6 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · realrebelai | 23.6 GB | 28.4 GB | fits · 11.8 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 18.7 GB | 23.5 GB | fits · 16.7 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 16.8 GB | 21.6 GB | fits · 18.6 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 15.1 GB | 19.9 GB | fits · 20.3 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 11.5 GB | 16.3 GB | fits · 23.9 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · realrebelai | 8.8 GB | 13.6 GB | fits · 26.6 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for LTX-2.5 and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run LTX-2.5 on a Mac 48 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the Mac 48 GB
A Mac with 48 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 40.2 GB of it by default (older macOS versions: about 38.7 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 48 GB: M3 Max, M4 Pro, M4 Max, M5 Pro, M5 Max (memory bandwidth 273–614 GB/s - the higher, the faster). Everything about Macs and local AI →
48 GB unified · ~40.2 GB for the GPU · 273–614 GB/s · Apple Silicon. Everything that runs on it →
05Questions
How much VRAM does LTX-2.5 need?
Around 13.6 GB with the smallest file (Q2_K) and 28.4 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 46.8 GB.
Which LTX-2.5 file should I download for the Mac 48 GB?
Q8_0 (23.6 GB) from realrebelai/LTX-2.5_GGUFs. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
How much do I need to download for LTX-2.5 on the Mac 48 GB?
51.7 GB: LTX-2.5-Distilled-Q8_0.gguf, gemma4-12b-with-proj-ltx-2.5-bf16.safetensors, ltx-2.5-video-vae-bf16.safetensors, ltx-2.5-audio-vae-bf16.safetensors.