porschefreak/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx-mlx-4Bit

Same weights, repacked vs nightmedia/Qwen3.6-35B-A3B-MTP-Holo3-Qwopus-Coder-qx64y-hi-mlx. Same weights in different files (re-saved, re-sharded or new metadata).

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