<![CDATA[I tried out the Gemma AI models from Google, running locally on my AMD APU (Ryzen 7 Pro 7840U with Radeon 780M) and asked it some questions about ZFS send / receive.]]>I tried out the Gemma AI models from Google, running locally on my AMD APU (Ryzen 7 Pro 7840U with Radeon 780M) and asked it some questions about ZFS send / receive.

gemma-4-26B-A4B-Q4_K_M:
14.29 tok/sec . The information, it generated, was factually correct and well laid out. Not the fasted, but surprisingly good.

gemma-4-E4B-Q4-K_M:
26 tok/sec. The information was completely wrong BS with made up parameters. The presentation was confident and well laid out. But it generated it quickly 😂
Bottom line: confidently incorrect at high speeds.

]]>https://board.circlewithadot.net/topic/d21af709-c1a0-4c0c-98ce-18d2e2f133bd/i-tried-out-the-gemma-ai-models-from-google-running-locally-on-my-amd-apu-ryzen-7-pro-7840u-with-radeon-780m-and-asked-it-some-questions-about-zfs-send-receive.RSS for NodeThu, 16 Apr 2026 21:41:54 GMTSat, 11 Apr 2026 16:36:32 GMT60<![CDATA[Reply to I tried out the Gemma AI models from Google, running locally on my AMD APU (Ryzen 7 Pro 7840U with Radeon 780M) and asked it some questions about ZFS send / receive. on Sun, 12 Apr 2026 13:15:42 GMT]]>@Larvitz

I'm currently testing whether I can build a simple Mastodon CLI tool – with Gemma4 for spell checking. 🤖

]]>https://board.circlewithadot.net/post/https://burningboard.net/users/tux/statuses/116391919107311996https://board.circlewithadot.net/post/https://burningboard.net/users/tux/statuses/116391919107311996Sun, 12 Apr 2026 13:15:42 GMT<![CDATA[Reply to I tried out the Gemma AI models from Google, running locally on my AMD APU (Ryzen 7 Pro 7840U with Radeon 780M) and asked it some questions about ZFS send / receive. on Sun, 12 Apr 2026 07:00:39 GMT]]>@Larvitz

You can now run this on your phone too:

Link Preview Image
Google's Gemma 4 puts free agentic AI on your phone and no data ever leaves the device

Google's new open-source model, Gemma 4, processes text, images, and audio completely on-device. Using agent skills, the AI can independently tap into tools like Wikipedia or interactive maps; no cloud required.

favicon

The Decoder (the-decoder.com)

]]>https://board.circlewithadot.net/post/https://burningboard.net/users/tux/statuses/116390444356954772https://board.circlewithadot.net/post/https://burningboard.net/users/tux/statuses/116390444356954772Sun, 12 Apr 2026 07:00:39 GMT