endless-frontier/BigBang-v1
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/5, Attention 261/392, MLP 280/399, Norms 100/247, lm_head 1/1, other 0/1
6 derivatives checked
- bartowski/endless-frontier_BigBang-v1-GGUF: Same weights, converted
- mradermacher/BigBang-v1-i1-GGUF: Quantization
- mradermacher/BigBang-v1-GGUF: Quantization
- AmixDigital/BigBang-v1-mtp-oQ2.7e: Quantization
- mlx-community/BigBang-v1-MLX-oQ4e: Quantization
- TheShed/BigBang-v1-W4A16-NVFP4-MTP: Quantization