ggml-org/Qwen3-Omni-30B-A3B-Thinking-GGUF

Same weights, converted vs Qwen/Qwen3-Omni-30B-A3B-Thinking. Same weights stored in another dtype (BF16 → BF16/F32), plus 192 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/193, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse