LTX-2.3 (22B, with audio) is a video generation model by Lightricks (22B; text encoder: Gemma 3 12B). Generates video and audio together; high compression suits longer clips.
Change precision, resolution or length →
| Precision | Model size | 480p, 5 s | 720p, 5 s |
|---|---|---|---|
| BF16 / FP16 (uncompressed) | 44.0 GB | 46.8 GB all in VRAM 59.8 GB | 48.1 GB all in VRAM 61.1 GB |
| FP8 (half size, near-lossless) | 22.4 GB | 25.2 GB all in VRAM 38.2 GB | 26.5 GB all in VRAM 39.5 GB |
| GGUF Q8_0 (similar to FP8) | 23.5 GB | 26.3 GB all in VRAM 39.3 GB | 27.6 GB all in VRAM 40.6 GB |
| GGUF Q4_K_S (popular low-VRAM choice) | 13.2 GB | 16.0 GB all in VRAM 29.0 GB | 17.3 GB all in VRAM 30.3 GB |
| GGUF Q3_K_S (lower quality) | 10.3 GB | 13.1 GB all in VRAM 26.1 GB | 14.4 GB all in VRAM 27.4 GB |
Bold = VRAM needed when ComfyUI swaps the text encoder and the model. "All in VRAM" = keeping both loaded. Text encoder assumed at FP8.
| GPU | VRAM | Best precision | VRAM needed | Verdict | Buy |
|---|---|---|---|---|---|
| RTX 4060 Ti 16GB previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7600 XT previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9060 XT 16GB | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 5060 Ti 16GB | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 6800 previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7800 XT previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 XT | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 9070 | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 4070 Ti SUPER previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 4080 previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 4080 SUPER previous gen | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 5070 Ti | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| RTX 5080 | 16 GB | GGUF Q3_K_S | 13.1 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7900 XT previous gen | 20 GB | GGUF Q4_K_S | 16.0 GB | ○ Runs with model swapping | Check price |
| RTX 3090 previous gen | 24 GB | GGUF Q4_K_S | 16.0 GB | ○ Runs with model swapping | Check price |
| Radeon RX 7900 XTX previous gen | 24 GB | GGUF Q4_K_S | 16.0 GB | ○ Runs with model swapping | Check price |
| RTX 4090 previous gen | 24 GB | GGUF Q4_K_S | 16.0 GB | ○ Runs with model swapping | Check price |
| RTX 5090 | 32 GB | FP8 | 25.2 GB | ○ Runs with model swapping | Check price |
ComfyUI also runs on AMD Radeon (ROCm) and Intel Arc, but setup is harder than on NVIDIA and some features (such as FP8 acceleration) are not supported.
→ Image & Video AI VRAM Calculator (all 15 models) / Local LLM VRAM Calculator
Estimates for ComfyUI, about ±20%. Model specs from the publisher's config files and released file sizes (checked October 2026).