ManniX-ITA/Qwen3.6-27B-A3B-Coder

Same weights, repacked vs Qwen/Qwen3.6-35B-A3B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/5, Attention 0/392, MLP 0/276, Norms 0/247, lm_head 0/1, other 0/1

3 derivatives checked

• ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF: Same weights, converted
• mradermacher/Qwen3.6-27B-A3B-Coder-i1-GGUF: Quantization
• mradermacher/Qwen3.6-27B-A3B-Coder-GGUF: Quantization

On the Hub · Downloads on Model Pulse