vadimayegorov/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B-mlx-fp16

Same weights, converted vs mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B. Same weights stored in another dtype (U32/BF16 → U32/F16).

Tensors changed: Embeddings 0/3, Norms 0/131, Attention 0/660, MLP 0/960, lm_head 0/3

On the Hub · Downloads on Model Pulse