DavidAU/Qwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored
MoE built from dense models vs Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1. DavidAU/Qwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored is a mixture of 6 experts assembled from dense models (mergekit-moe style): expert 0 is an exact copy of Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 226 of 226 identical.
3 derivatives checked
- mradermacher/Qwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored-i1-GGUF: Quantization
- mradermacher/Qwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored-GGUF: Same weights, converted
- Solaren/Qwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored-Q8_0-GGUF: Quantization