LTX-2.5 FP8 + NVFP4 Quantized Weights

Components

Quantization Details

Transformer (FP8)

• Each 2D bf16 weight matrix cast to float8_e4m3fn with per-tensor absmax scaling
• Scale stored as {key}_scale (float32) alongside each FP8 weight
• 1775 weight matrices quantized, 2574 dense tensors kept as-is
• Compatible with ltx-pipelines QuantizationKind.FP8_SCALED_MM (auto-detected from filename)

Text Encoder (NVFP4)

• torchao NVFP4DynamicActivationNVFP4WeightConfig with use_dynamic_per_tensor_scale=True, use_triton_kernel=True
• Each quantized linear stored as 4 keys: .weight (uint8), .weight_scale (float8_e4m3fn), .weight_scale_2 (float32), .torchao_nvfp4 (JSON metadata)
• 334 linear layers quantized, 352 dense tensors preserved
• Same on-disk format as vonkaiser/MiniMax-H3-NVFP4 text encoder

VRAM Budget (all resident, no CPU offload)

Source

• diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors
• text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors

License