LatitudeGames/Equinox-31B
Full fine-tune vs google/gemma-4-31B-it. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 4/4, Norms 0/523, other 0/62, MLP 261/261, Attention 338/338
6 derivatives checked
- LatitudeGames/Equinox-31B-GGUF: Quantization (fewer layers)
- bartowski/LatitudeGames_Equinox-31B-GGUF: Same weights, converted (fewer layers)
- mradermacher/Equinox-31B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Equinox-31B-GGUF: Quantization (fewer layers)
- jashepp/Equinox-31B-i1-MXFP4-GGUF: Quantization (fewer layers)
- Abiray/Equinox-31B-GGUF: Quantization (fewer layers)