Gryphe/Pantheon-Proto-RP-1.8-30B-A3B
Full fine-tune vs Qwen/Qwen3-30B-A3B-Base. Fine-tune: 94% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 107/193, MLP 2611/2613, Attention 192/192, lm_head 1/1
4 derivatives checked
- bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF: Same weights, converted
- mradermacher/Pantheon-Proto-RP-1.8-30B-A3B-i1-GGUF: Quantization
- mradermacher/Pantheon-Proto-RP-1.8-30B-A3B-GGUF: Quantization
- allura-forge/q3-30b-rc1: Full fine-tune