LTX-Video 13B (0.9.8) on 8 GB of VRAM
Not entirely. Even Q2_K is 1.0 GB over 8 GB, so ComfyUI keeps part of it in system RAM. The last of the pre-LTX-2 video models from Lightricks (July 2025). No audio, T5 text encoder, and much lighter than LTX-2.
Offload
Not entirely in VRAM, but it can still run.
Nothing fits entirely, but Q2_K (4.7 GB) overflows by only about 1.0 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
Best fileQ2_K
File size4.7 GB
VRAM needed~9.0 GB
System RAM32 GB+
Memory map · 8 GB GPU9.0 GB needed · 1.0 GB over 8 GB
05 GB9 GB
Weights Q2_K · 4.7 GBWorking memory · 3.5 GBReserve · 0.8 GBSpills to system RAM · 1.0 GB
calculated How this is counted.
Also try the FP8 file (15.7 GB) on NVIDIA GPUs. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →
01Other amounts of VRAM
02Every file, on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Lightricks | 28.6 GB | 32.9 GB | 24.9 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 14.0 GB | 18.3 GB | 10.3 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Lightricks | 15.7 GB | 20.0 GB | 12.0 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 10.9 GB | 15.2 GB | 7.2 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 9.8 GB | 14.1 GB | 6.1 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 8.8 GB | 13.1 GB | 5.1 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 6.5 GB | 10.8 GB | 2.8 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · QuantStack | 4.7 GB | 9.0 GB | spills 1.0 GB | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3.5 GB of working memory for LTX-Video 13B and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | LTXV-13B-0.9.8-dev-Q2_K.gguf Q2_K · QuantStack/LTXV-13B-0.9.8-dev-GGUF | models/unet | 4.7 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn_scaled.safetensors T5-XXL FP8 (scaled) · comfyanonymous/flux_text_encoders | models/text_encoders | 5.2 GB | Download → |
| VAE | LTXV-13B-0.9.8-dev-VAE.safetensors LTXV 13B 0.9.8 VAE (standalone, QuantStack) · QuantStack/LTXV-13B-0.9.8-dev-GGUF | models/vae | 2.5 GB | Download → |
| Total download · keep about the same free on disk | 12.4 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.