Nanthasit/sakthai-vision-7b
Not comparable yet vs Qwen/Qwen2-VL-2B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 729/291 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs Qwen/Qwen2-VL-2B-Instruct. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 729/291 match), usually an architecture llama.cpp's name map doesn't cover yet.