Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Mistral Large 4. Parent comment
In practice, you will be able to run models a bit bigger than 35B.
https://unsloth.ai/docs/models/qwen3.8-next
38GB of vram resident. more tk/s, more prefill.
In practice, you will be able to run models a bit bigger than 35B.
https://unsloth.ai/docs/models/qwen3.8-next