ggml-org/Qwen3-235B-A22B-GGUF
Same weights, converted vs Qwen/Qwen3-235B-A22B. Same weights stored in another dtype (BF16 → F16/F32), plus 282 new tensors.
Tensors changed: Embeddings 0/1, MLP 0/94, Norms 0/377, Attention 0/376, lm_head 0/1
Same weights, converted vs Qwen/Qwen3-235B-A22B. Same weights stored in another dtype (BF16 → F16/F32), plus 282 new tensors.
Tensors changed: Embeddings 0/1, MLP 0/94, Norms 0/377, Attention 0/376, lm_head 0/1