LTX-2.5 (22B) on 12 GB of VRAM
Not entirely. Even Q2_K is 1.6 GB over 12 GB, so ComfyUI keeps part of it in system RAM. The July 2026 LTX, with a custom Gemma 4 12B text encoder. GGUF sizes differ a lot between uploaders because they mix precisions differently; figures here use realrebelai's distilled files.
Nothing fits entirely, but Q2_K (8.8 GB) overflows by only about 1.6 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
01Other amounts of VRAM
02Every file, on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Lightricks | 42.0 GB | 46.8 GB | 34.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · realrebelai | 23.6 GB | 28.4 GB | 16.4 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 18.7 GB | 23.5 GB | 11.5 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 16.8 GB | 21.6 GB | 9.6 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 15.1 GB | 19.9 GB | 7.9 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 11.5 GB | 16.3 GB | 4.3 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · realrebelai | 8.8 GB | 13.6 GB | spills 1.6 GB | 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.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | LTX-2.5-Distilled-Q2_K.gguf Q2_K · realrebelai/LTX-2.5_GGUFs | models/unet | 8.8 GB | Download → |
| Text encoder | gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors Gemma 4 12B + LTX projection INT8 (convrot) · Lightricks/LTX-2.5 | models/text_encoders | 15.4 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 | 26.0 GB | |||
Alternatives: Gemma 4 12B + LTX projection BF16 (26.3 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). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 26.0 GB of RAM while loaded, 32.0 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
At 15.4 GB even the smallest Gemma 4 12B (custom LTX-2.5 build) file is too big for 12 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 26.3 GB, INT8 15.4 GB. Why the encoder does not count against VRAM →