Entries matching “qat”

QUASAR-trained Blackwell W4A4 build of Muse Glimmer 30B at 21.8 GiB, reporting 20% lower KL to BF16 than Red Hat's NVFP4 W4A4 checkpoint.

A quantization-aware-trained Q4_0 GGUF of Muse Glimmer 30B for llama.cpp. On held-out tokens it measures closer to BF16 than Meta's official Q4_K_M: 0.0213 vs 0.0228 KL and 95.9% vs 95.6% top-token agreement.