mradermacher/Qwen3-Desert.Coder.MoE-8X0.6B-GGUF

Same weights, converted vs WithinUsAI/Qwen3-Desert.Coder.MoE-8X0.6B. Same weights stored in another dtype (F16 → F16/F32), plus 84 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112

On the Hub · Downloads on Model Pulse