microsoft/FrogBoss-32B-2510
Full fine-tune vs Qwen/Qwen3-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 238/257, MLP 192/192, Attention 256/256, lm_head 1/1
4 derivatives checked
- mradermacher/FrogBoss-32B-2510-i1-GGUF: Quantization
- mradermacher/FrogBoss-32B-2510-GGUF: Quantization
- DevQuasar/microsoft.FrogBoss-32B-2510-GGUF: Same weights, converted
- SofiTesfay2010/FrogBoss-35B-Flash: Different architecture