AbteeXAILab/lumynax-multimodal-qwen25-vl-72b-instruct-gguf

Quantization vs Qwen/Qwen2.5-VL-72B-Instruct. AbteeXAILab/lumynax-multimodal-qwen25-vl-72b-instruct-gguf is a GGUF quantization (Q4_K_M) of the same weights: 401 tensors match exactly and 562 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/560, lm_head 0/1

On the Hub · Downloads on Model Pulse