Joakimpalm-Zen/gpt-oss-20b-keep30-MXFP4-GGUF
Quantization vs openai/gpt-oss-20b. Joakimpalm-Zen/gpt-oss-20b-keep30-MXFP4-GGUF is a GGUF quantization (MXFP4/Q8_0) of the same weights: 145 tensors match exactly and 98 within quantization error.
Tensors changed: Norms 0/49, Attention 0/192, lm_head 0/1, Embeddings 0/1