DevQuasar-12/google.gemma-3-4b-it-qat-int4-unquantized-GGUF

Same weights, converted (fewer layers) vs google/gemma-3-4b-it-qat-int4-unquantized. DevQuasar-12/google.gemma-3-4b-it-qat-int4-unquantized-GGUF matches part of google/gemma-3-4b-it-qat-int4-unquantized (444 of its 883 tensors; the rest of google/gemma-3-4b-it-qat-int4-unquantized has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse