#qat

The latest AI and developer news about #qat, with the original source and a short summary.

QUASAR 4-bit QAT checkpoints for Qwen3.5, Gemma 4 and Muse Glimmer: closer to BF16 than Google’s and NVIDIA’s 4-bit releases

New NVFP4 and GGUF checkpoints use quantization-aware distillation to achieve lower KL divergence than reference 4-bit models from NVIDIA, Google, and community quantizers.

·2·2026.10.16 03:00

Gemma 4 QAT MTP Heads Released and Bug Fixed

MTP heads for Gemma 4 QAT models have been released, along with news of a fix for a llama.cpp parallel execution bug.

·3·2026.06.07 06:00

PickGemma 4 QAT Models: Optimizing Model Compression for Mobile and Laptop Efficiency

Google has released Gemma 4 models with QAT technology applied to boost efficiency on mobile and laptop environments.

·1·2026.06.06 01:00