GPT-4 trounces everything else available. I'd say that 70b is about 3.5 level, unless you're doing something where finetuning greatly benefits you.
13b is alright for toy applications, but the difference to gpt 3.5 (let alone gpt4) is huge.
13b is alright for toy applications, but the difference to gpt 3.5 (let alone gpt4) is huge.
I bought a dodgy used mining 3090 last year and now my computer is writing poetry in the terminal in real time.