EpistemeAI/metatune-gpt20b-R1.1
Quantization vs unsloth/gpt-oss-20b-unsloth-bnb-4bit. unsloth/gpt-oss-20b-unsloth-bnb-4bit is a quantized version of the other (U8/F16).
3 derivatives checked
- mradermacher/metatune-gpt20b-R1.1-i1-GGUF: Quantization
- bartowski/EpistemeAI_metatune-gpt20b-R1.1-GGUF: Same weights, converted
- mradermacher/metatune-gpt20b-R1.1-GGUF: Quantization