Re:Experimenting with Local LLMs on macOS
by segmondy on Monday September 08, 2025 @03:17PM
(#45172619)
I know this is false, DeepSeekv3.1, GLM4.5, KimiK2-0905, Qwen-235B are all solid open models. Last night, I vibed rough 1300 lines of C server code in about an hour. 0 compilation error, ran without errors and got the job done. I want to meet this experienced programmer that can knock out 1300 lines of C code in an hour.
[ Parent
| on HN ]
Re:Experimenting with Local LLMs on macOS
by nomel on Monday September 08, 2025 @04:31PM
(#45173566)
Without knowing what you were doing with that 1300 lines of code, there's not much insight that can be had from this.
Re:Experimenting with Local LLMs on macOS
by codazoda on Monday September 08, 2025 @05:56PM
(#45174553)
How much machine do you have to be able to run Qwen-235B locally?
Re:Experimenting with Local LLMs on macOS
by drusepth on Monday September 08, 2025 @06:32PM
(#45174954)
Are 235B models classified as local LLMs? I guess they probably are, but others in this thread are probably looking more toward 20B-30B models and sizes that generally fit on the RAM you'd expect in average or slightly-higher-end hardware.
My beefy 3D gamedev workstation with a 4090 and 128GB RAM can't even run a 235B model unless it's extremely quantized (and even then, only at like single-digit tokens/minute).
Re:Experimenting with Local LLMs on macOS
by oblio on Tuesday September 09, 2025 @01:44AM
(#45177852)
Can you run any of those models without $20 000 worth of hardware that uses as much power and makes as much noise as a small factory?
Re:Experimenting with Local LLMs on macOS
by segmondy on Wednesday September 10, 2025 @03:22PM
(#45202402)
I run them with under $3,000 hardware and inference is about 500-600watts with no noise.
Re:Experimenting with Local LLMs on macOS
by brookst on Tuesday September 09, 2025 @09:00AM
(#45181363)
I’m a mediocre C programmer on my best day and I assure you a highly competent programmer could probably use 200 lines of code to do what I achieve in 1300.
Just counting lines is not a good proxy for how much effort it would take a good programmer.
(And I am 100% pro LLM coding, just saying this isn’t a great argument)