OpenMOSE/Qwen3.5-REAP-262B-A17B

Same weights, converted vs Qwen/Qwen3.5-397B-A17B. Same weights stored in another dtype (BF16/F32 → BF16).

Tensors changed: lm_head 0/1, Embeddings 0/4, Attention 0/528, MLP 0/352, Norms 0/306

2 derivatives checked

• RobinsonLabs/Qwen3.5-REAP-262B-A17B-abliterated-GGUF: Quantization
• OpenMOSE/Qwen3.5-REAP-262B-A17B-GGUF: Quantization

On the Hub · Downloads on Model Pulse