mlx-community/Qwen2.5-Coder-32B-Instruct-bf16

Same weights, repacked vs Qwen/Qwen2.5-Coder-32B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1

2 derivatives checked

• featherless-ai-quants/mlx-community-Qwen2.5-Coder-32B-Instruct-bf16-GGUF: Quantization
• tensorblock/Qwen2.5-Coder-32B-Instruct-bf16-GGUF: Quantization

On the Hub · Downloads on Model Pulse