Yes. You don't get Fable at the $20 level.

It was the wrong time for the GP to drop that subscription from $200 to $20, because $200 gets you a metric assload of cognition while $20 gets you nothing beyond what a local model running on your own graphics card can deliver.

▲

sunaookami 3 hours ago | parent | next [-]

You heavily underestimate the value of the 20$ subscription.

	▲	CamperBob2 2 hours ago \| parent [-]
		Not according to this very story, I'm not. Who's right? Consistent, predictable behavior is valuable, even more so given the nondeterministic nature of LLMs. Nondeterminism combined with unpredictability might as well be randomness.

▲

Foobar8568 4 hours ago | parent | prev | next [-]

I had $310 in (free) credit that I used on fable, and I still had a part of the $200 subscription at that time. You know, subscriptions don't end the moment you click on cancel.

▲

skeledrew 3 hours ago | parent | prev [-]

> $20 gets you nothing beyond what a local model running on your own graphics card can deliver.

I'd guess you're deliberately exaggerating here, but still. I've never clocked the actual tokens/second, but I'm on the $20 plan and get ~15M tokens/month for fully utilized weekly quotas (checked couple months ago). Meanwhile the best I've been able to get locally was ~8 tokens/second with Qwen3.6 35B A3B, which is wildly painful for coding sessions and gets a maximum ~20M tokens in a month... if it's going 24/7.

Just wanted to stick some empirical data here, given that statement.

▲

bot403 3 hours ago | parent | next [-]

I run local models. Your op is absolutely wrong. To get a local LLM is at least a $1500 investment at the cheapest. $5000 if you want usable.

At $1500 that's 75 months of $20/mo Claude which are MUCH better models than you can run locally.

▲

owebmaster 2 hours ago | parent | next [-]

This calc is off. Using Claude for a few hours with the $20 plan will hit the limit for a week while the local model can process things 24/7.

	▲	skeledrew an hour ago \| parent [-]
		Running 24/7 doesn't make sense though, unless you're providing a service to others. But if it's just you then there has to be time taken to review+test what's being done and craft new prompts. And if that local hardware isn't decent enough it's impractical for anything serious that's interactive. Meanwhile I just take the Claude limits on stride and break, or if a week is pretty heavy then I augment with DeepSeek Flash via OpenRouter (does wonders in a single turn when I have Claude prompt it to handle implementation slices).

▲

CamperBob2 2 hours ago | parent | prev [-]

At $1500 that's 75 months of $20/mo Claude which are MUCH better models than you can run locally.

The point raised by this very article is that you can't depend on that. It's Flowers for Algernon As A Service.

	▲	nozzlegear an hour ago \| parent [-]
		If you already have that $1500 setup though..

▲

nozzlegear an hour ago | parent | prev [-]

Ouch. I get ~45t/s with Qwen3.6 35B A3B, and around ~70-80 with my current model Ornith 1.5 35B A3B. Local models work a treat IMO if you've got decent hardware for it.