71–80 of 276 posts
* General Q&A
* Specific to programming - mostly Python and Go.
I forgot the command now, but I did run a command that allowed MacOS to allocate and use maybe 28 GB of RAM to the GPU for use with LLMs.
I agree that it's kind of magical that you can download a ~10GB file and suddenly your laptop is running something that can summarize text, answer questions and even reason a bit. The trick is balancing model size vs RAM: 12B–20B is about the upper limit for a 16GB machine without it choking. What I find interesting is that these models don't actually hit Apple's Neural Engine, they run on the GPU via Metal. Core ML…
We don't even need one big model good at everything. Imagine loading a small model from a collection of dozens of models depending on the tasks you have in mind. There is no moat.
I'm running Hermes Mistral and the very first thing it did was start hallucinating. I recently started an audio dream journal and want to keep it private. Set up whisper to transcribe the .wav file and dump it in an Obsidian folder. The plan was to put a local llm step in to clean up the punctuation and paragraphs. I entered instructions to clean the transcript without changing or adding anything else. Hermes respond…
It’s often been assumed that accuracy and ‘correctness’ would be easy to implement on computers because they operate on logic, in some sense. It’s originality and creativity that would be hard, or impossible because it’s not logical. Science Fiction has been full of such assumptions. Yet here we are, the actual problem is inventing new heavy enough training sticks to beat our AIs out of constantly making stuff up and…
More fundamental than the training data is the fact that the generative outputs are statistical, not logical. This is why they can produce a sequence of logical steps but still come to incorrect or contradictory conclusions. This is also why they tackle creativity more easily since the acceptable boundaries of creative output is less rigid. A photorealistic video of someone sawing a cloud in half can still be entertaining art despite the logical inconsistencies in the idea.
Is anyone working on software that lets you run local LLMs in the browser? In theory, it should be possible, shouldn't it? The page could hold only the software in JavaScript that uses WebGL to run the neural net. And offer an "upload" button that the user can click to select a model from their file system. The button would not upload the model to a server - it would just let the JS code access it to convert it into…
Transformers.js ( https://huggingface.co/docs/transformers.js/en/index ) is this. Some demos (should work in Chrome and Firefox on Windows, or Firefox Nightly on macOS and Linux): https://huggingface.co/spaces/webml-community/llama-3.2-webg... loads a 1.24GB Llama 3.2 q4f16 ONNX build https://huggingface.co/spaces/webml-community/janus-pro-webg... loads a 2.24 GB DeepSeek Janus Pro model which is multi-modal for outp…
I tried some of the demos of transformers.js but they all seem to load the model from a server. Which is super slow. I would like to have a page the lets me use any model I have on my disk.
Is anyone working on software that lets you run local LLMs in the browser? In theory, it should be possible, shouldn't it? The page could hold only the software in JavaScript that uses WebGL to run the neural net. And offer an "upload" button that the user can click to select a model from their file system. The button would not upload the model to a server - it would just let the JS code access it to convert it into…
Demos here: https://webmachinelearning.github.io/webnn-samples/ I'm not sure any of them allow you to select a model file from disk, but that should be entirely straightforward.
I agree that it's kind of magical that you can download a ~10GB file and suddenly your laptop is running something that can summarize text, answer questions and even reason a bit. The trick is balancing model size vs RAM: 12B–20B is about the upper limit for a 16GB machine without it choking. What I find interesting is that these models don't actually hit Apple's Neural Engine, they run on the GPU via Metal. Core ML…
I agree that it's kind of magical that you can download a ~10GB file and suddenly your laptop is running something that can summarize text, answer questions and even reason a bit. The trick is balancing model size vs RAM: 12B–20B is about the upper limit for a 16GB machine without it choking. What I find interesting is that these models don't actually hit Apple's Neural Engine, they run on the GPU via Metal. Core ML…
I too found that interesting that Apple's Neural Engine doesn't work with local LLMs. Seems like Apple, AMD, and Intel are missing the AI boat by not properly supporting their NPUs in llama.cpp. Any thoughts on why this is?
I agree that it's kind of magical that you can download a ~10GB file and suddenly your laptop is running something that can summarize text, answer questions and even reason a bit. The trick is balancing model size vs RAM: 12B–20B is about the upper limit for a 16GB machine without it choking. What I find interesting is that these models don't actually hit Apple's Neural Engine, they run on the GPU via Metal. Core ML…
I'm on a 128GB M4 macbook. This is "powerful" today, but it will be old news in a few years.
These models are just about getting as good as the frontier models.