lmstudio-community/OpenCoder-1.5B-Instruct-GGUF
Quantization vs infly/OpenCoder-1.5B-Instruct. lmstudio-community/OpenCoder-1.5B-Instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 49 tensors match exactly and 170 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96