Nothing will come close to Opus 4.6 here. You will be able to fit a destilled 20B to 30B model on your GPU.
Gpt-oss-20B is quite good in my testing locally on a Macbook Pro M2 Pro 32GB.
The bigger downside, when you compare it to Opus or any other hosted model, is the limited context. You might be able to achieve around 30k.
Hosted models often have 128k or more. Opus 4.6 has 200k as its standard and 1M in api beta mode.
There are local models with larger context, but the memory requirements explode pretty quickly so you need to lower parameter count or resort to heavy quantization. Some local inference platforms allow you to place the KV cache in system memory (while still otherwise using GPU). Then you can just use swap to allow for even very long contexts, but this slows inference down quite a bit. (The write load on KV cache is just appending a KV vector per inferred token, so it's quite compatible with swap. You won't be wearing out the underlying storage all that much.)
Regarding the $200 subscription.
For Claude Code with Opus (and also Sonnet) you need that, yes.
I had ChatGPT Codex GPT5.2 high reasoning running on my side project for multiple hours the last nights.
It created a server deployment for QA and PROD + client builds.
It waited for the builds to complete, got the logs from Github Actions and fixed problems.
Only after 4 days of this (around 2-4 hours) active coding I reached the weekly limit for the ChatGPT Plus Plan (23€).
Far better value so far.
To be fully honest, it fucked up one flyway script. I have to fix this now my self :D. Will write a note in the Agent.md to never alter existing scripts.
But the work otherwise was quite solid and now my server is properly deployed.
If I would switch between High reasoning for Planing and Middle reasoning for coding, I would get even more usage.
But seriously, I can't help but think that this proliferation of massive numbers of iterations on these models and productizations of the models is an indication that their owners have no idea what they are doing with any of it. They're making variations and throwing them against the wall to see what sticks.
Don't get me wrong, but somebody has to operate an exit node and somehow there needs to be a consensus on the protocol + routing.
If the network is only earth bound fixed wireless, the distance might be small enough that the state comes for the operator itself...
This raises the cost of running this network from just money to life threat.
Getting many open source satellites up in orbit might not be feasible.
Agreed that nothing is fully trustless on Earth. The point isn’t eliminating operators, it’s avoiding single points of coercion and failure. One exit can be shut down but many exits and type of networks (includong more alternative infra like the Guifi.net’s meshnetworks in Spain for example) across jurisdictions raise the cost from “call a CEO” to sustained political pressure or directly a CEO that has control over an entire network and its also a billionaire CEO with a messiah complex, far-right leanings and tendency to drug abuse.
Absolute decentralization is impossible. Reducing capture and increasing resilience is not. That’s a meaningful difference.
Said that, I’m happy with Starlink as an extra actor for a healthy mix of ISPs and networks that brings resilience.
Got to say, I like the current Android versions.
In the early days I flashed my Motorola Defy every second month with some cool new ROM.
Always rooted and Xposed, always enabling something new.
Now I run a S23 Ultra and after two years it still does everything I need.
OneUI 8.0 and Android 16.
For work (app de) I also have a Pixel 7a, always with the newest Android Beta.
Also works well.
Even the entry level phones work OK to pretty good now.
My Samsung A16 5G (also for work) functions surprisingly well for 150€.
> Now I run a S23 Ultra and after two years it still does everything I need.
Maybe, but it is fully under Google and Samsung's control, and is choke full of spyware. You couldn't pay me to use a stock (Googled) Android phone for this reason alone.
Back when I used Android phones, tweaking was pretty important to me too. I still remember when I installed CyanogenMod on a Motorola XT1565, those were the days... Eventually, LineageOS, and then some new phones happened, not all of which were rootable, though I eventually ended up with a OnePlus 7 Pro which was pretty tweakable and even opened the possibility of bootloader re-locking, until a TWRP bug wiped my device and I pretty much stopped tweaking. Was never quite able to get EdXposed working right again...
How well is rooting supported on these newer Android versions/devices? If I install LineageOS on my device, for example, I can be reasonably sure that Magisk will work fine. But how well does it work on a stock, locked-down ROM?
Most devices doesn't have unlockable bootloaders now thus you can't even root them unless it was a popular device and a temporary /finicky hack was found.
Fully agree.
ChatGPT is often very confident and tells me that X and Y is absolutely wrong in the code.
It then answers with something worse...
It also does rarely say "sorry, I was wrong" when the previous output was just plain lies. You really need to verify every answer because it is so confident.
I fully switched to Gemini 3 Pro.
Looking into an Opus 4.5 subscription too.
My GF on the other side prefers ChatGPT for writing tasks quite a lot (school teacher classes 1-4).
When you have enough experience and the project fits, this is the way to go.
They don't pay for your time.
They pay for your output and you can bill them on the output.
Not quickly but if somebody puts enough money on the table, the fabs change too.
All about cost and return.
Micron just axed their brand crucial (end customer RAM and SSD) because they will only sell to database centers from now on.
Let's see if this demand truly holds.
I'm still unsure.
Currently nobody makes money with AI.
There will be a correction (if I can trust my magic crystal ball ;) )
Got to say, those prices were quite cheap.
I also upgraded my home server to 32GB RAM and paid something like 55€.
Now we can just wait for some bubble to pop...
Sadly everything in the general direction of RAM or SSD chips is getting more expensive because a lot of production capacity is redistributed to serve AI chips and everything around.
Even lower end GPUs are getting more expensive even if they are not really useful for AI.
But they still contain <some> chips and ram which is in high demand.
So yes, Apple will likely also have to pay higher priceses when they renew their contracts.
The bigger downside, when you compare it to Opus or any other hosted model, is the limited context. You might be able to achieve around 30k. Hosted models often have 128k or more. Opus 4.6 has 200k as its standard and 1M in api beta mode.
reply