---
license: apache-2.0
base_model: google/gemma-4-E2B-it-qat-mobile-transformers
tags:
  - gguf
  - gemma4
  - qat
---

# gemma-4-E2B-it-qat-mobile — GGUF (GPU-friendly)

GGUF of Google's gemma-4 E2B QAT-mobile checkpoint using only tensor types with
GPU kernels in llama.cpp. Quantization mirrors the checkpoint's own per-module
QAT bit-map (`quantization_config`): attention and layers 0–14 MLPs → `Q4_0`,
2-bit-trained modules (remaining MLPs, `token_embd`, `output`) → `Q2_K`,
per-layer gates → `Q8_0`. SRQ activation scales are dropped (not representable
in GGUF).

wikitext-2 fidelity vs the bf16 QAT reference: PPL 88.3 (ref 80.6), mean KLD
0.20 — comparable to TQ2_0-based packs, without the CPU-only ternary types.