DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2
MoE built from dense models vs Qwen/Qwen3-0.6B. DavidAU/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2 is a mixture of 4 experts assembled from dense models (mergekit-moe style): expert 0 is an exact copy of Qwen/Qwen3-0.6B's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 227 of 227 identical.
4 derivatives checked
- mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-i1-GGUF: Quantization
- mradermacher/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-GGUF: Same weights, converted
- justneedsomeavailableusername/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-mlx-4Bit: Quantization
- nightmedia/Qwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-q8-mlx: Quantization