Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs
Researchers have developed new post-training quantization techniques for the Ideogram 4.0 text-to-image diffusion transformer. Their INT8 W8A8 method maintains FP8 quality on consumer GPUs lacking FP8 tensor cores, outperforming NF4 quantization. Additionally, their GGUF Q4_K quantization offers a superior quality-memory trade-off compared to NF4. AI
IMPACT Enables running advanced text-to-image models on lower-end hardware, potentially broadening access and use cases.