mradermacher/gpt-oss-20b-Esper3.1-GGUF

Quantization vs ValiantLabs/gpt-oss-20b-Esper3.1. mradermacher/gpt-oss-20b-Esper3.1-GGUF is a GGUF quantization (Q8_0) of the same weights: 193 tensors match exactly and 98 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse