Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

What changed

Our latest paper, Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs, asks a question that the field has mostly left open: once a model has already been through structural compression, not just quantization, how well does that recovery step actually work, and what is the right way to do it? We introduce Quantization-Aware Healing (QAH), and applied to a GPT-OSS 120B model compressed to 60B parameters and quantized to MXFP4, it produces a model that beats its own full-precision (bfloat16) version on 7 of 9 benchmarks. The 4-bit model ends up smaller, cheaper to run, and more accurate than the checkpoint it was quantized from.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

• LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
• Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
• Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

• LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation similarity 0.22
• Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA similarity 0.20
• Bringing Nunchaku 4-bit Diffusion Inference to Diffusers similarity 0.14