README.md

metadata

library_name: llama.cpp
base_model: gpt-oss-20b
license: apache-2.0
tags:
  - gguf
  - quantized
  - q8_0
datasets:
  - HillPhelmuth/ChessReasoning_OpenAIOss_Template

gpt-oss-20B Chess Analysis (GGUF)

• Quantization: q8_0
• Converted with: python llama.cpp/convert_hf_to_gguf.py gpt-oss-20b-hf --outfile gpt-oss-20b-q8_0.gguf --outtype q8_0
• Intended for chess analysis workloads with llama.cpp-compatible runtimes.