This is the first usable gpt-oss-20b heretic I know of.
#1
by
IrisColt
- opened
I tried SerialKicked's quants of your model ( https://huggingface.co/SerialKicked/GPT-OSS-20B-Heretic-GGUF/ )
During testing I found that Q8_0 performs well, but for the MXFP4, the successive quantizations somehow compromised its natural defenses... and as a result the MXFP4 quant actually performs better and is astonishingly fast.
I’ll run more tests, but so far the pairing Coder3101 (heretic) + SerialKicked (quant) is outstanding. As I said also to SerialKicked, in the end you produced a gpt-oss-20b that truly works and is blazingly fast. No small feat.