mradermacher/gemma4-e2b-Snowfox-hf-GGUF

Same weights, converted (fewer layers) vs MichaelAnthony/gemma4-e2b-Snowfox-hf. mradermacher/gemma4-e2b-Snowfox-hf-GGUF matches part of MichaelAnthony/gemma4-e2b-Snowfox-hf (505 of its 1951 tensors; the rest of MichaelAnthony/gemma4-e2b-Snowfox-hf has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 36 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/227, MLP 0/105, other 0/71, Attention 0/100

On the Hub · Downloads on Model Pulse