# Gemma 4 mobile-mixture QAT with TQ2_0 2-bit layers (UD-Q2_K_XL for E2B/E4B) > Already covered: gemma-4-qat-gguf-conversion-f16-versus-bf16-scal.md holds the TQ2_0 plus negative-scaler conversion into UD-Q2_K_XL, the E2B (2.19 GB, 61 TQ2_0 tensors, KLD 0.00409) and E4B (3.22 GB, 2 TQ2_0 tensors, KLD 0.00102) rows; no new claim found. Parent: [Mac local LLMs: Quantization formats and methods](https://llms-explorer.com/tree/mac-local-llms-quantization-formats-and-methods/) · 1 facets · 1 facts · page: https://llms-explorer.com/tree/gemma-4-mobile-mixture-qat-with-tq2-0-2-bit-laye/ ## Facts - Already covered: gemma-4-qat-gguf-conversion-f16-versus-bf16-scal.md holds the TQ2_0 plus negative-scaler conversion into UD-Q2_K_XL, the E2B (2.19 GB, 61 TQ2_0 tensors, KLD 0.00409) and E4B (3.22 GB, 2 TQ2_0 tensors, KLD 0.00102) rows; no new claim found. — source: `asserted`