Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

LTX-2.5 (22B) on 6 GB of VRAM

Video model · 22BAny 6 GB GPUData 2026-09-25
No
No, not realistically.

Even the smallest file (Q2_K, 8.8 GB) needs about 13.6 GB, far beyond 6 GB. It may start with heavy offloading, but this is not a realistic everyday setup. Pick a smaller model or a GPU with more memory.

Best fileQ2_K
File size8.8 GB
VRAM needed~13.6 GB
System RAM48 GB+
Memory map · 6 GB GPU13.6 GB needed · 7.6 GB over 6 GB
07 GB14 GB
Weights Q2_K · 8.8 GBWorking memory · 4.0 GBReserve · 0.8 GBSpills to system RAM · 7.6 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
ModelLTX-2.5-Distilled-Q2_K.gguf
Q2_K · realrebelai/LTX-2.5_GGUFs
models/unet8.8 GBDownload →
Text encodergemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors
Gemma 4 12B + LTX projection INT8 (convrot) · Lightricks/LTX-2.5
models/text_encoders15.4 GBDownload →
VAEltx-2.5-video-vae-bf16.safetensors
LTX-2.5 video VAE (DiffVAE) BF16 · Lightricks/LTX-2.5
models/vae1.5 GBDownload →
Also neededltx-2.5-audio-vae-bf16.safetensors
LTX-2.5 audio VAE + vocoder BF16 · Lightricks/LTX-2.5
models/vae0.4 GBDownload →
Total download · keep about the same free on disk26.0 GB

Alternatives: Gemma 4 12B + LTX projection BF16 (26.3 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. 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 read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 48 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 26.0 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 32.0 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every file, on 6 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Lightricks
42.0 GB46.8 GB40.8 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · realrebelai
23.6 GB28.4 GB22.4 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · realrebelai
18.7 GB23.5 GB17.5 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · realrebelai
16.8 GB21.6 GB15.6 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · realrebelai
15.1 GB19.9 GB13.9 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · realrebelai
11.5 GB16.3 GB10.3 GB too bignoticeable loss of detailHugging Face →
Q2_K ←
GGUF · realrebelai
8.8 GB13.6 GB7.6 GB too bigheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 4 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

Gemma 4 12B (custom LTX-2.5 build): 26.3 GB as 16-bit, 15.4 GB as INT8. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 6 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.