qingy2024/GRMR-V3-Q4B
Full fine-tune vs unsloth/Qwen3-4B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 110/145, MLP 108/108, Attention 144/144
4 derivatives checked
- mradermacher/GRMR-V3-Q4B-i1-GGUF: Quantization
- mradermacher/GRMR-V3-Q4B-GGUF: Same weights, converted
- qingy2024/GRMR-V3-Q4B-GGUF: Same weights, converted
- DevQuasar/qingy2024.GRMR-V3-Q4B-GGUF: Same weights, converted