apodex/Apodex-1.1-mini
Full fine-tune vs Qwen/Qwen3.5-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 280/1165, lm_head 1/1, Embeddings 1/5, Attention 238/392, other 0/1, Norms 129/247
16 derivatives checked
- abenzerps/Apodex-1.1-mini-GGUF: Quantization
- IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2.1-GGUF: Quantization
- bartowski/apodex_Apodex-1.1-mini-GGUF: Same weights, converted
- apodex/Apodex-1.1-mini-NVFP4: Quantization
- apodex/Apodex-1.1-mini-FP8: Quantization
- IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF: Quantization
- apodex/Apodex-1.1-mini-GPTQ-Int4: Quantization
- mradermacher/Apodex-1.1-mini-i1-GGUF: Quantization
- kataguru/Apodex-1.1-mini-Finnish-Uncensored-GGUF: Quantization
- mradermacher/Apodex-1.1-mini-GGUF: Quantization
- kataguru/Apodex-1.1-mini-Finnish-GGUF: Quantization
- abenzerps/Apodex-1.1-mini-MLX: Quantization
- stefanprodan/Apodex-1.1-mini-oQ4e-mtp: Quantization
- Joonix71/Apodex-1.1-mini-MTPLX-Balance: Quantization
- nicolasembleton/Apodex-1.1-mini-MLX-6bit: Quantization
- kataguru/Apodex-1.1-mini-Finnish-GPTQ-Int4: Quantization