mradermacher/PT-22B-V2-GGUF
Quantization vs NewEden-Forge/PT-22B-V2. mradermacher/PT-22B-V2-GGUF is a GGUF quantization (Q8_0) of the same weights: 153 tensors match exactly and 534 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/153, MLP 0/228, Attention 0/304, lm_head 0/1