introvoyz041/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit-mlx-4Bit

Same weights, repacked vs lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: lm_head 0/3, Embeddings 0/3, Norms 0/145, MLP 0/324, Attention 0/432

On the Hub · Downloads on Model Pulse