FrontisAI/Frontis-MA1-35B
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/5, Attention 251/392, MLP 280/399, Norms 100/247, lm_head 1/1, other 0/1
4 derivatives checked
- bartowski/FrontisAI_Frontis-MA1-35B-GGUF: Same weights, converted
- mradermacher/Frontis-MA1-35B-i1-GGUF: Quantization
- mradermacher/Frontis-MA1-35B-GGUF: Quantization
- FrontisAI/Frontis-MA1-35B-GGUF: Quantization