lmstudio-community/Qwen2-VL-72B-Instruct-GGUF

Quantization vs Qwen/Qwen2-VL-72B-Instruct. lmstudio-community/Qwen2-VL-72B-Instruct-GGUF is a GGUF quantization (Q8_0) 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