Loom-Labs/Apollo-1-4B
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 90% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 110/145, MLP 108/108, Attention 144/144
9 derivatives checked
- mradermacher/Nous-1-4B-i1-GGUF: Quantization
- mradermacher/Nous-V1-4B-i1-GGUF: Quantization
- mradermacher/Apollo-1-4B-GGUF: Same weights, converted
- mradermacher/Apollo-1-4B-i1-GGUF: Quantization
- mradermacher/Nous-V1-4B-GGUF: Same weights, converted
- prithivMLmods/Nous-V1-4B-GGUF: Same weights, converted
- mradermacher/Nous-1-4B-GGUF: Same weights, converted
- Loom-Labs/Apollo-1-4B-GGUF: Same weights, converted
- prithivMLmods/Nous-1-4B-f32-GGUF: Same weights, converted