kingjones777/Gemma-4-31B-it-ROCmFP4-GGUF

Quantization (fewer layers) vs google/gemma-4-31B-it. kingjones777/Gemma-4-31B-it-ROCmFP4-GGUF matches part of google/gemma-4-31B-it (772 of its 1188 tensors; the rest of google/gemma-4-31B-it has no counterpart). On the shared part: kingjones777/Gemma-4-31B-it-ROCmFP4-GGUF is a GGUF quantization (Q8_0_ROCMFPX) of the same weights: 361 tensors match exactly and 1 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/361

On the Hub · Downloads on Model Pulse