Apfel

“Apfel[0] has exposed it as a CLI”

“I like being able to pipe output into a local LLM to get an explanation of the output.”

“Apfel is a cool project; it's been the only thing tempting me to upgrade to Tahoe”

“Something I grab on a regular basis, especially for doing simple education of folks about the basics of using LLMs”

“Apfel is very useful, thanks for the effort.”

“If you've got a mac, you can use this to play around with it:”

“There's a project called Apfel that wraps it in a CLI.”

“you can install the apfel stuff if you're on a mac and want a quick available onboard cli option”

“No model download necessary”

“local model + tool calling with no cloud dependency is a nice setup”

“I was able to confirm that it actually runs on ANE, I'm impressed.”

“Seems like it struggles as much as a normal person”

“Rust version goofed with lines of comments and code intertwined.”

“I appreciate the project itself! It's just these flashy LLM-generated webpages are really misleading.”

“Hugely non-deterministic: repeat queries give vastly different responses.”

“I'm sorry, I don't see a 'Carol Bring' in your contacts”

“It's absolutely free and open source”

“love the simple website and typography”

“I was able to install it on my older macos 15, but it aborted on execution.”

“Extremely oversold landing page, very marketing heavy for what it is.”

“just the marketing goes hard a bit”

“Apple's model came out on top—best accuracy in 6 out of 10 cases in the backtest.”

“Local AIs are the future in times of limited resources.”

“zero cost and fully local is hard to beat for quick throwaway tasks”

“It's a nice LLM because it seems fairly decent and it loads instantly”

“it being limited to English from what I can tell is quite a downsite for me”

“I like the approach of running everything locally.”

“I like the idea and the clarity to explain the usage”

“They offer it as an option but default it to false!”

“Cool tool but I don't get why these websites make idiotic claims”

“I've been playing with it for some time now I'm impressed.”

“great for shell scripts though (my major use case now)”

“The combined (input/output) context window length is 4K.”

“I'm running Sequoia still and get an error about model not found.”

“the 4k token context window and the super hard guardrails”

“it isn't very good. And the guardrails are hilariously bad.”

“this is real neat. I'll give it a spin.”

“without calling home or downloading extra local models”

“using it in bash scripts that just work without calling home / out or incurring extra costs feels super powerful.”

“Apple Ai on the command line”