aimeri/spoomplesmaxx-flash-35B-A3
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-35B-A3B-Base. aimeri/spoomplesmaxx-flash-35B-A3 matches part of Qwen/Qwen3.5-35B-A3B-Base (1026 of its 1811 tensors; the rest of Qwen/Qwen3.5-35B-A3B-Base has no counterpart). On the shared part: Fine-tune: 99% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 240/392, lm_head 1/1, Embeddings 1/4, Attention 232/388, Norms 98/241
2 derivatives checked
- mradermacher/spoomplesmaxx-flash-35B-A3-i1-GGUF: Quantization
- mradermacher/spoomplesmaxx-flash-35B-A3-GGUF: Quantization