self-hosted/ai
§01·model · /models

LightX2V

videoactiveApache-2.0

Step-distilled + CFG-distilled acceleration of Wan2.1-T2V-14B by the LightX2V team - 4-step inference without classifier-free guidance (Self-Forcing bidirectional distillation). fp8/int8 quantized variants run on GPUs as small as the RTX 4060. Apache-2.0.

§02·GPUs that run this model
19 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarksRecipe
RTX 306012GB30~0recipecheck ↗
RTX 3080 Ti12GB30~0recipecheck ↗
RTX 309024GB30~0recipecheck ↗
RTX 3090 Ti24GB30~0recipecheck ↗
RTX 4060 Ti 16GB16GB40~0recipecheck ↗
RTX 407012GB40~0recipecheck ↗
RTX 4070 Super12GB40~0recipecheck ↗
RTX 4070 Ti12GB40~0recipecheck ↗
RTX 4070 Ti Super16GB40~0recipecheck ↗
RTX 408016GB40~0recipecheck ↗
RTX 4080 Super16GB40~0recipecheck ↗
RTX 409024GB40~0recipecheck ↗
RTX 5060 Ti16GB50~0recipecheck ↗
RTX 507012GB50~0recipecheck ↗
RTX 5070 Ti16GB50~0recipecheck ↗
RTX 508016GB50~0recipecheck ↗
RTX 509032GB50~0recipecheck ↗
RX 7800 XT16GBamd~0recipecheck ↗
RX 7900 XTX24GBamd~0recipecheck ↗

benchmarked·~ runs via recipe (not benchmarked)· untested·doesn't fit