Re:Show HN: I taught GPT-OSS-120B to see using Google Lens a...
by vkaufmann on Wednesday February 11, 2026 @07:40AM
(#46974214)
GPT-OSS-120B runs like hell on my DGX Spark
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.
> Jinja threw a bunch of errors and GPT-OSS couldn't make tool calls.
This was an issue for a week or two when GPT-OSS initially launched, as none of the inference engines had properly implemented support for it, especially around tool calling. I'm running GPT-OSS-120b MXFP4 with LM Studio and directly with llama.cpp, the recent versions handle it well and I have no errors.
However, when I've tried either 120b or 20b with additional quantization (not the "native" MXFP4 ones), I've seen that they're having troubles with the tool syntax too.
> Not llama
What does your original comment mean then? You said llama was "strictly" better than GPT-OSS, which specific model variant are you talking about or you miswrote somehow?