0xSero/Qwen3.6-28B
Same weights, repacked vs Qwen/Qwen3.6-35B-A3B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Attention 0/280, Norms 0/131, MLP 0/160, lm_head 0/1
5 derivatives checked
- barozp/Qwen3.6-28B-REAP20-A3B-GGUF: Same weights, converted
- mradermacher/Qwen3.6-28B-REAP-i1-GGUF: Quantization
- mradermacher/Qwen3.6-28B-REAP-GGUF: Quantization
- DjeDjeB/Qwen3.6-28B-REAP-i1-GGUF: Quantization
- DjeDjeB/Qwen3.6-28B-REAP20-A3B-GGUF: Same weights, converted