In your view, which are couple different companies that aren’t very big (not FAANG level yet), but you think will become quite successful? Which of them are mission driven and you’d be sad if they later become “corrupted”?
Isn’t “what” the easy part? I thought the leadership is more about why they are doing what they are doing and why is that important/not important. Something which LLMs are not great at today, but aren’t terrible and can make some good guesses at times.
I would not think that LLMs would make very good leadership decisions, mostly because they're too malleable and too easy to manipulate. I do think they're very helpful in helping leaders assess their own context and situation and thereby make better decisions.
I have been trying to run Qwen Coder models (8B at 4bit) on my M3 Pro 18GB behind Ollama and connecting codex CLI to it. The tool usage seems practically zero, like it returns the tool call in text JSON and codex CLI doesn’t run the tool (just displays the tool call in text). Has anyone succeeded in doing something like this? What am I missing?
What would a good coding model to run on an M3 Pro (18GB) to get Codex like workflow and quality? Essentially, I am running out quick when using Codex-High on VSCode on the $20 ChatGPT plan and looking for cheaper / free alternatives (even if a little slower, but same quality). Any pointers?
Nothing. This summer I set up a dual 16GB GPU / 64GB RAM system and nothing I could run was even remotely close. Big models that didn't fit on 32gb VRAM had marginally better results but were at least of magnitude slower than what you'd pay for and still much worse in quality.
I gave one of the GPUs to my kid to play games on.
I'm running unsloth/GLM-4.7-Flash-GGUF:UD-Q8_K_XL via llama.cpp on 2x 24G 4090s which fits perfectly with 198k context at 120 tokens/s – the model itself is really good.
Short answer: there is none. You can't get frontier-level performance from any open source model, much less one that would work on an M3 Pro.
If you had more like 200GB ram you might be able to run something like MiniMax M2.1 to get last-gen performance at something resembling usable speed - but it's still a far cry from codex on high.
at the moment, I think the best you can do is qwen3-coder:30b -- it works, and it's nice to get some fully-local llm coding up and running, but you'll quickly realize that you've long tasted the sweet forbidden nectar that is hosted llms. unfortunately.
They are spending hundreds of billions of dollars on data centers filled with GPUs that cost more than an average car and then months on training models to serve your current $20/mo plan. Do you legitimately think there's a cheaper or free alternative that is of the same quality?
I guess you could technically run the huge leading open weight models using large disks as RAM and have close to the "same quality" but with "heat death of the universe" speeds.
Not sure if it's me but at least for my use cases (software devl, small-medium projects) Claude Opus + Claude Code beats by quite a margin OpenCode + GLM 4.7. At least for me Claude "gets it" eventually while GLM will get stuck in a loop not understanding what the problem is or what I expect.
Right, GLM is close But not close enough. If I have to spend $200 for Opus fallback i may as well not use it always. Still an unbelievable option if $200 is a luxury, the price-per-quality is absurd.
"run" as in run locally? There's not much you can do with that little RAM.
If remote models are ok you could have a look at MiniMax M2.1 (minimax.io) or GLM from z.ai or Qwen3 Coder. You should be able to use all of these with your local openai app.
(1) Are you optimizing your content for LLMs yet?
(2) What do you think AI traffic will look like 6–12 months from now?
(3) What kinds of AI visibility issues have you run into?
Happy to answer anything about how we built the tool or what’s under the hood too.
