mradermacher/Qwen2.5VL-7B-Instruct-i1-GGUF

Quantization (fewer layers) vs gaoqie/Qwen2.5VL-7B-Instruct-fire. mradermacher/Qwen2.5VL-7B-Instruct-i1-GGUF matches part of gaoqie/Qwen2.5VL-7B-Instruct-fire (339 of its 729 tensors; the rest of gaoqie/Qwen2.5VL-7B-Instruct-fire has no counterpart). On the shared part: mradermacher/Qwen2.5VL-7B-Instruct-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 141 tensors match exactly and 198 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse