Why does Jim look odd? Does he have a different face?
This would be a fantastic time to try to organize labor in tech. We have needed unions badly for decades now. I hope the AI debacle coupled with rising socialist sentiments in the face of global fascism can finally give us the momentum to get there.
Agreed, all the mass layoffs are really helping build class consciousness among the labor aristocrats.
if we don’t manage to push our salaries up from this garbage, we failed.
Demand a raise.
One jas to Knox how expensive LLMs are by trying to run one at home. Tried running it myself, figured out I need more than 128GiB of RAM and thousand dollars in grahics card. Figured out a $5 openai per month is cheaper, and also understood they are burning money by providing a free service and 20$ subscription.
You should be able to get very decent performance with 128gb vram running Qwen 3.6 with something like https://github.com/itigges22/ATLAS especially if you run MTP https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF
A friend of mine gets something like 50 tokens a second with it, and output quality is quite decent.
How does it compare to largest deepseek ans Claude opus 4.6? I hot used to blazing fast speed and accurate results. I’m not buying a server and 128 GB of RAM just to run a model similar to gpt-4.
ATLAS has some benchmarks in the repo, and it’s comparable to opus 4.6, you don’t actually even need 128gb model for that. An 8 bit quantized model will run with around 32gb and still perform quite well.
