LTX-2.3 (22B) on 8 GB of VRAM
Not entirely. Even Q4_K_M is 11.1 GB over 8 GB, so ComfyUI keeps part of it in system RAM. The March 2026 update of LTX-2, grown to 22B parameters.
The smallest sensible file, Q4_K_M (14.3 GB), needs about 19.1 GB - 11.1 GB more than 8 GB GPU has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
01Other amounts of VRAM
02Every file, on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit GGUF · unsloth | 42.0 GB | 46.8 GB | 38.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 22.8 GB | 27.6 GB | 19.6 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 17.8 GB | 22.6 GB | 14.6 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 16.1 GB | 20.9 GB | 12.9 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · unsloth | 14.3 GB | 19.1 GB | 11.1 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 10.8 GB | 15.6 GB | 7.6 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 8.3 GB | 13.1 GB | 5.1 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for LTX-2.3 and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | ltx-2.3-22b-dev-Q4_K_M.gguf Q4_K_M · unsloth/LTX-2.3-GGUF | models/unet | 14.3 GB | Download → |
| Text encoder | gemma_3_12B_it_fp8_scaled.safetensors Gemma 3 12B FP8 (scaled) · Comfy-Org/ltx-2 | models/text_encoders | 13.2 GB | Download → |
| VAE | ltx-2.3-22b-dev_video_vae.safetensors LTX-2.3 video VAE · unsloth/LTX-2.3-GGUF | models/vae | 1.5 GB | Download → |
| Also needed | ltx-2.3-22b-dev_audio_vae.safetensors LTX-2.3 audio VAE · unsloth/LTX-2.3-GGUF | models/vae | 0.4 GB | Download → |
| Also needed | ltx-2.3-22b-dev_embeddings_connectors.safetensors LTX-2.3 text embeddings connectors (projection) · unsloth/LTX-2.3-GGUF | models/text_encoders | 2.3 GB | Download → |
| Total download · keep about the same free on disk | 31.7 GB | |||
Alternatives: Gemma 3 12B FP4 mixed (9.4 GB); Gemma 3 12B BF16 (24.4 GB). FP4 files are listed only as alternatives unless the GPU is an RTX 50 (Blackwell). Only for some workflows: LTX-2.3 spatial upscaler x2 1.1 (1.0 GB, official two-stage template). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 31.7 GB of RAM while loaded, 37.7 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
At 9.4 GB even the smallest Gemma 3 12B file is too big for 8 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 24.4 GB, FP8 13.2 GB, FP4 mixed 9.4 GB. Why the encoder does not count against VRAM →