unsloth/Qwen3.6-35B-A3B-MTP-GGUF
Same weights, converted vs Qwen/Qwen3.6-35B-A3B. Same weights stored in another dtype (BF16 → BF16/F32), plus 170 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/200, Attention 0/40, lm_head 0/1
5 derivatives checked
- plunderstruck/Qwen3.6-35B-A3B-MTP-ROCmFP4-GGUF: Quantization
- LucianoM39/Qwen3.6-35B-A3B-UD-Q4_K_XL-Mesh-LLM: Quantization (fewer layers)
- jcbtc/qwen3.6-35b-a3b-crown-halo-mtp-dynamic: Quantization
- YTan2000/Qwen3.6-35B-A3B-MTP-TQ3_4S: Quantization
- raulvidis/Qwen3.6-35B-A3B-ROCmFP4_FAST-GGUF: Quantization