LTX-Video 13B (0.9.8) VRAM requirements
The last of the pre-LTX-2 video models from Lightricks (July 2025). No audio, T5 text encoder, and much lighter than LTX-2.
TypeVideo
Parameters13B
Fits entirely from10 GB
8-bit or better from19 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 28.6 GB | 32.9 GB | 33 GB | the original weights | Lightricks/LTX-Video → |
| Q8_0 | 14.0 GB | 18.3 GB | 19 GB | practically identical to the original | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| FP8 | 15.7 GB | 20.0 GB | 20 GB | practically identical to the original | Lightricks/LTX-Video → |
| Q6_K | 10.9 GB | 15.2 GB | 16 GB | very close to the original | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| Q5_K_M | 9.8 GB | 14.1 GB | 15 GB | close; small differences in fine detail | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| Q4_K_M | 8.8 GB | 13.1 GB | 14 GB | good; some loss in fine detail and text | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| Q3_K_M | 6.5 GB | 10.8 GB | 11 GB | noticeable loss of detail | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| Q2_K | 4.7 GB | 9.0 GB | 10 GB | heavy loss; a last resort | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
“Needed” = file + 3.5 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for LTX-Video 13B
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for LTX-Video 13B → Planning bigger images or longer clips? Open the calculator →
04By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| Arc B570 10 GB | 10 GB | Tight | Q2_K | 9.0 GB |
| RTX 3080 10 GB | 10 GB | Tight | Q2_K | 9.0 GB |
| RTX 2080 Ti 11 GB | 11 GB | Tight | Q3_K_M | 10.8 GB |
| Arc B580 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 2060 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 3060 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 3080 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 3080 Ti 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 4070 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 4070 Super 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 4070 Ti 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 5070 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RX 7700 XT 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RX 9070 GRE 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| Arc A770 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 4080 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 5080 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 7600 XT 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 7800 XT 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 9060 XT 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 9070 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 9070 XT 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 18.3 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 3090 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 4090 24 GB | 24 GB | Runs well | FP8 | 20.0 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | Q8_0 | 18.3 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | Q8_0 | 18.3 GB |
| RTX 5090 32 GB | 32 GB | Runs well | FP8 | 20.0 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Not practical | Q2_K | 9.0 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Not practical | Q2_K | 9.0 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 13.1 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q2_K | 9.0 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RX 7800M 12 GB | 12 GB | Tight | Q3_K_M | 10.8 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RX 7900M 16 GB | 16 GB | Runs | Q6_K | 15.2 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | FP8 | 20.0 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 32.9 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 32.9 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Tight | Q3_K_M | 10.8 GB |
| Mac 18 GB | 14.4 GB | Runs | Q5_K_M | 14.1 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 18.3 GB |
| Mac 32 GB | 26.8 GB | Runs well | Q8_0 | 18.3 GB |
| Mac 36 GB | 30.2 GB | Runs well | Q8_0 | 18.3 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 32.9 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 32.9 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 32.9 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 32.9 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 32.9 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 32.9 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 32.9 GB |
05Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| T5-XXL FP8 (scaled) t5xxl_fp8_e4m3fn_scaled.safetensors | models/text_encoders | 5.2 GB | text encoder · smaller, recommended | Download → |
| T5-XXL FP16 t5xxl_fp16.safetensors | models/text_encoders | 9.8 GB | text encoder · alternative | Download → |
| LTXV 13B 0.9.8 VAE (standalone, QuantStack) LTXV-13B-0.9.8-dev-VAE.safetensors | models/vae | 2.5 GB | with GGUF files · GGUF / diffusion-model-only route | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
06Where the files go in ComfyUI
| File | Folder | Loader node |
|---|---|---|
| Diffusion model (.safetensors: 16-bit, FP8, INT8) | ComfyUI/models/diffusion_models | Load Diffusion Model |
| GGUF file (.gguf) | ComfyUI/models/unet | Unet Loader (GGUF) - from the ComfyUI-GGUF node pack |
| Text encoder | ComfyUI/models/text_encoders | Load CLIP / DualCLIPLoader (or the GGUF versions) |
| VAE | ComfyUI/models/vae | Load VAE |
07Measured and reported results
No measured results yet. Send yours.
08Training a LoRA for LTX-Video 13B
No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →
09Every file tracked for LTX-Video 13B
| File | Type | Size | Repo |
|---|---|---|---|
| ltxv-13b-0.9.8-distilled.safetensors (distilled) | 16-bit | 28.58 GB | Lightricks/LTX-Video → |
| ltxv-13b-0.9.8-dev.safetensors (dev) | 16-bit | 28.58 GB | Lightricks/LTX-Video → |
| ltxv-13b-0.9.8-distilled-fp8.safetensors (distilled) | FP8 | 15.69 GB | Lightricks/LTX-Video → |
| ltxv-13b-0.9.8-dev-fp8.safetensors (dev) | FP8 | 15.69 GB | Lightricks/LTX-Video → |
| LTXV-13B-0.9.8-dev-Q8_0.gguf (dev) | Q8_0 | 14.01 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q6_K.gguf (dev) | Q6_K | 10.89 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q5_K_M.gguf (dev) | Q5_K_M | 9.82 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q5_K_S.gguf (dev) | Q5_K_S | 9.18 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q4_K_M.gguf (dev) | Q4_K_M | 8.82 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q4_K_S.gguf (dev) | Q4_K_S | 7.98 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q3_K_M.gguf (dev) | Q3_K_M | 6.51 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q3_K_S.gguf (dev) | Q3_K_S | 5.86 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-dev-Q2_K.gguf (dev) | Q2_K | 4.72 GB | QuantStack/LTXV-13B-0.9.8-dev-GGUF → |
| LTXV-13B-0.9.8-distilled-Q8_0.gguf (distilled) | Q8_0 | 14.01 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q6_K.gguf (distilled) | Q6_K | 10.89 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q5_K_M.gguf (distilled) | Q5_K_M | 9.82 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q5_K_S.gguf (distilled) | Q5_K_S | 9.18 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q4_K_M.gguf (distilled) | Q4_K_M | 8.82 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q4_K_S.gguf (distilled) | Q4_K_S | 7.98 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q3_K_M.gguf (distilled) | Q3_K_M | 6.51 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q3_K_S.gguf (distilled) | Q3_K_S | 5.86 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
| LTXV-13B-0.9.8-distilled-Q2_K.gguf (distilled) | Q2_K | 4.72 GB | QuantStack/LTXV-13B-0.9.8-distilled-GGUF → |
Text encoder T5-XXL. Legacy line - superseded by LTX-2 / 2.3 / 2.5 (audio+video).