Today, I got Gemma4:12b-it-qat running at a good 70 tokens per second on the Lenovo, Nvidia 4070, llama.cpp, with multi token prediction. Got Qwen3.8:27b running at a good 6 tokens per second. Yeah that one ain't going anywhere fast. I'm downloading Gemma4:26b to see how fast it can go on this poor machine. Also, got Emacs with Emacspeak working with an Eloquence speech server, for the new Eloquence for Linux. That's how I'm using Mastodon on Linux currently.#foss #emacs #ai
Related
Should I be happy, or should I be mad.... #robotic #robots #ai https://gizmodo.com/its-official-no-man-can-outrun-our-ro...
Should I be happy, or should I be mad.... #robotic #robots #ai https://gizmodo.com/its-official-no-man-can-outrun-our-robot-overlords-2000799565
AI Isn’t Outthinking Mathematicians. It’s Out-Remembering Them."A human mathematician can hold only a small number of un...
AI Isn’t Outthinking Mathematicians. It’s Out-Remembering Them."A human mathematician can hold only a small number of unfamiliar elements in mind simultaneously. An AI model can ke...
【西川和久の不定期コラム】ローカルAIの超新星！Qwen3.8-27B×DeepSeek Harnessを早速試すhttps://pc.watch.impress.co.jp/docs/column/nishikawa/2133158.ht...
【西川和久の不定期コラム】ローカルAIの超新星！Qwen3.8-27B×DeepSeek Harnessを早速試すhttps://pc.watch.impress.co.jp/docs/column/nishikawa/2133158.html#impress #市場 #AI #その他 #記事集約用 #レビュー