LucianoM39/Gemma-4-E4B-it-Q4_0-Mesh-LLM

Same weights, repacked (fewer layers) vs google/gemma-4-E4B-it-qat-q4_0-gguf. LucianoM39/Gemma-4-E4B-it-Q4_0-Mesh-LLM matches part of google/gemma-4-E4B-it-qat-q4_0-gguf (20 of its 666 tensors; the rest of google/gemma-4-E4B-it-qat-q4_0-gguf has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: other 0/5, Norms 0/8, Attention 0/4, MLP 0/3

On the Hub · Downloads on Model Pulse