Re:Show HN: I taught GPT-OSS-120B to see using Google Lens a...
by embedding-shape on Wednesday February 11, 2026 @09:16AM
(#46975201)
The MXFP4 variant I suppose? My setup (RTX Pro 6000) does around ~140 tok/s with llama.cpp, around 160 tok/s with vLLM.
[ Parent
| on HN ]