// Open-model VRAM table · family
LTX Video: local deployment & VRAM
8 open-weight models from Lightricks (11 official repos incl. quantised builds).
official orgs: Lightrickslatest 2026-07-23memory = estimate
01Video generation (8)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| LTX-2.5 | — | — | — | — | — | Custom licence – read it | 2026-07-23 |
| LTX-2.3 | — | — | — | — | — | Custom licence – read it | 2026-03-04 |
| LTX-2 | 18.9B | 42.0 GB | 13.1 GB | 16GB GPU | Mac 24GB | Custom licence – read it | 2026-01-03 |
| LTX-Video-0.9.8-13B-distilled ↗ | 13B | 29.2 GB | 9.2 GB | 12GB GPU | Mac 16GB | Custom licence – read it | 2025-07-17 |
| LTX-Video-0.9.7-distilled ↗ | 13B | 29.2 GB | 9.2 GB | 12GB GPU | Mac 16GB | Custom licence – read it | 2025-05-14 |
| LTX-Video-0.9.7-dev ↗ | 13B | 29.2 GB | 9.2 GB | 12GB GPU | Mac 16GB | Custom licence – read it | 2025-05-13 |
| LTX-Video-0.9.5 | 1.92B | 4.7 GB | 1.8 GB | 8GB GPU | Mac 16GB | Custom licence – read it | 2025-03-16 |
| LTX-Video | 1.92B | 4.7 GB | 1.8 GB | 8GB GPU | Mac 16GB | Custom licence – read it | 2024-10-31 |
02Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Wan · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →