# Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

arXiv: https://arxiv.org/abs/2606.12280 · HTML: https://mlsanity.com/paper/2606.12280/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 24 of 24)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [PTQD: Accurate Post-Training Quantization for Diffusion Models](https://mlsanity.com/paper/2305.10657/) (2023)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation](https://mlsanity.com/paper/2406.02540/) (2024)
- [FonTS: Text Rendering with Typography and Style Controls](https://mlsanity.com/paper/2412.00136/) (2024)
- [CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encoder](https://mlsanity.com/paper/2412.17225/) (2024)
- [PQD: Post-training Quantization for Efficient Diffusion Models](https://mlsanity.com/paper/2501.00124/) (2024)
- [FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers](https://mlsanity.com/paper/2503.15465/) (2025)
- [Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution](https://mlsanity.com/paper/2602.01273/) (2026)
- [DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers](https://mlsanity.com/paper/2605.16732/) (2026)
- [Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization](https://mlsanity.com/paper/2409.00492/) (2024)
- [Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion](https://mlsanity.com/paper/2412.06661/) (2024)
- [Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling](https://mlsanity.com/paper/2509.01624/) (2025)
- [Accelerating Rectified Flow Models via Trajectory-Aware Caching](https://mlsanity.com/paper/2605.16789/) (2026)
- [HDGlyph: A Hierarchical Disentangled Glyph-Based Framework for Long-Tail Text Rendering in Diffusion Models](https://mlsanity.com/paper/2505.06543/) (2025)
- [Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V](https://mlsanity.com/paper/2605.27003/) (2026)
- [Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers](https://mlsanity.com/paper/2606.00957/) (2026)

## Built on by (most cited first, 1 of 1)

- [Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0](https://mlsanity.com/paper/2606.14598/) (2026)

## Abstract (arXiv)

We study post-training quantization (PTQ) of Ideogram 4.0, a 9.3B flow-matching diffusion transformer (DiT) that realizes classifier-free guidance with two separate-weight copies of a single-stream backbone and is conditioned by a Qwen3-VL text encoder, targeting Ampere RTX~3090 GPUs, which lack FP8 tensor cores. Because Ideogram~4.0 is trained on structured JSON captions, we evaluate every variant under schema-valid JSON prompts produced by an LLM expander built to Ideogram's published caption specification, and score them with a battery spanning human-preference (HPSv2), CLIP, and PickScore for standalone quality; PP-OCR exact-match and edit distance for text; and PSNR/SSIM/LPIPS for fidelity to the FP8 reference (the highest-precision public checkpoint) output. On a 300-prompt benchmark with paired bootstrap confidence intervals, an INT8 W8A8 recipe (per-channel weights, per-token dynamic activations, SmoothQuant, and bf16 protection of a small high-fragility layer set) is statistically indistinguishable from FP8 on CLIP and PickScore (paired CIs include zero) and within ~0.004 HPSv2, and, at its 8-bit size, is the most faithful reproduction of the FP8 output (LPIPS 0.243 vs 0.277/0.306 for the half-size 4-bit baselines; the INT8-Q4_K gap excludes zero). A GGUF Q4_K quantization reaches the same standalone quality as the published NF4 baseline at the same on-disk size, making it the Pareto choice on the quality-memory frontier. We further show that under JSON prompts all four variants reach parity on standalone quality, the variants separate on fidelity and text rendering, not on aggregate image-quality scores, and that text legibility, near-zero when the model is prompted with raw strings, reaches 55% OCR exact-match under the JSON captions it expects. We release the INT8 W8A8 and GGUF Q4_K quantized weights on Hugging Face under a gated, non-commercial license.