Blazed-Forge/Gemma-4-Gemsicle-31B-GGUF

Quantization (fewer layers) vs Blazed-Forge/Gemma-4-Gemsicle-31B. Blazed-Forge/Gemma-4-Gemsicle-31B-GGUF matches part of Blazed-Forge/Gemma-4-Gemsicle-31B (772 of its 1188 tensors; the rest of Blazed-Forge/Gemma-4-Gemsicle-31B has no counterpart). On the shared part: Blazed-Forge/Gemma-4-Gemsicle-31B-GGUF is a GGUF quantization (Q8_0/BF16) of the same weights: 362 tensors match exactly and 410 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230

On the Hub · Downloads on Model Pulse