[flagged]
Claude may require identity verification in some cases
61–70 of 105 posts
Re: Claude may require identity verification in some cases
#62Earlier quoted context omitted.
Qwen3 runs locally on reasonable hardware, and is comparable to a mid-2025 Claude Sonnet (albeit possibly rather slower) . Local models are chasing the online frontier models pretty hard. So worst case, that's the fallback (FWIW, YMMV) edit: Qwen-3.5 MoE (and other local MoE models like it)
Whats "reasonable hardware"?
If you want something off the shelf get a MacBook Pro M5 (base "Pro" CPU) with 48GB RAM:
Gemma 4 31B Q6: 9tok/s, I'd say it is smarter than GPT-4o, but yeah it's slow. Good for coding.
Gemma 4 26B A4B Q4: 50tok/s. Feels faster than ChatGPT 5.4, but not as smart (as it reasons less). Good for general chatting and research.
Re: Claude may require identity verification in some cases
#63Earlier quoted context omitted.
Whats "reasonable hardware"?
People have tried to run Qwen3-235B-A22B-Thinking-2507 on 4x $600 used, Nvidia 3090s with 24 GB of VRAM each (96 GB total), and while it runs, it is too slow for production grade ( You can quantize it of course, but if the idea is "as close to Sonnet as possible," then while quantized models are objectively more efficient they are sacrificing precision for it. So next step is to up that speed, so we're at 4x $1300, N…
I may have genuinely new data for you.
Qwen3.5-35B-A3B is reported to perform slightly better than the model you mentioned.
It runs fine but non-optimal on a single 3090 with even 131072 tokens of context , and due to the hybrid attention architecture, the memory usage and compute scale rather less drastically than ctx^2. I've had friends with smaller cards still getting work out of it. Generation is at around 20 tokens/sec on that 3090 (without doing anything special yet) . You'll need enough DRAM to hold the bits of the model that don't fit. Nothing to write home about, but genuinely usable in a pinch or for tasks that don't need immediate interactivity.
It's the first local model that passes my personal kimbench usability benchmark at least. Just be aware that it is extremely verbose in thinking mode. Seems to be a qwen thing.
(edit: On rechecking my numbers; I now realize I can possibly optimize this a lot better)
Re: Claude may require identity verification in some cases
#64You will be reported to DHS if you ask Claude about Maven and the bombing of girls schools in Iran.
Prove it
Re: Claude may require identity verification in some cases
#65Earlier quoted context omitted.
People have tried to run Qwen3-235B-A22B-Thinking-2507 on 4x $600 used, Nvidia 3090s with 24 GB of VRAM each (96 GB total), and while it runs, it is too slow for production grade ( You can quantize it of course, but if the idea is "as close to Sonnet as possible," then while quantized models are objectively more efficient they are sacrificing precision for it. So next step is to up that speed, so we're at 4x $1300, N…
I may have genuinely new data for you. Qwen3.5-35B-A3B is reported to perform slightly better than the model you mentioned. It runs fine but non-optimal on a single 3090 with even 131072 tokens of context , and due to the hybrid attention architecture, the memory usage and compute scale rather less drastically than ctx^2. I've had friends with smaller cards still getting work out of it. Generation is at around 20 tok…
With respect, this isn't "new data" it is an anecdote. And it kind of represents exactly the problem I was talking about above:
- Qwen is near Sonnet 4.5!
- How do I run that?
- [Starts talking about something inferior that isn't near Sonnet 4.5].
It is this strange bait/switch discussion that happens over and over. Least of all because Sonnet has a 200K context window, and most of these ancdotes aren't for anywhere near that context size.
Re: Claude may require identity verification in some cases
#66The next level on the escalation ladder a few years later would be social credit score verification.
Re: Claude may require identity verification in some cases
#67Earlier quoted context omitted.
This will do absolutely nothing to prevent those actors from accessing Claude... they already recruit young unemployed Americans to do proxy job interviews[0][1], etc. They'll just pay young unemployed Americans to do verification for them. [0] https://www.tradingview.com/news/cointelegraph:6192f38e3094b... [1] https://youtube.com/watch?v=QebpXFM1ha0
That sounds likely to increase their costs and create new opportunities to get caught. Not a silver bullet but not "absolutely nothing". Like how anti-money laundering laws don't wipe out all crime, but are still worthwhile.
Get caught how? They don’t tell the person what they’re going to use the accounts for or who will use it. The star buyer patsy knows nothing.
On the scale of intelligence budgets this would be in the realm of petty cash.
Re: Claude may require identity verification in some cases
#68Peter Thiel corporation.
Logged into Claude. Cancelled my max sub. That was that. Now on to migration.
Re: Claude may require identity verification in some cases
#69Earlier quoted context omitted.
I may have genuinely new data for you. Qwen3.5-35B-A3B is reported to perform slightly better than the model you mentioned. It runs fine but non-optimal on a single 3090 with even 131072 tokens of context , and due to the hybrid attention architecture, the memory usage and compute scale rather less drastically than ctx^2. I've had friends with smaller cards still getting work out of it. Generation is at around 20 tok…
With respect, this isn't "new data" it is an anecdote. And it kind of represents exactly the problem I was talking about above: - Qwen is near Sonnet 4.5! - How do I run that? - [Starts talking about something inferior that isn't near Sonnet 4.5]. It is this strange bait/switch discussion that happens over and over. Least of all because Sonnet has a 200K context window, and most of these ancdotes aren't for anywhere…
You're not wrong; but... imho it's closer to Sonnet 4.0 [1] on my personal benchmark [2]. And I HAVE run it at just over 200Ktoken context, it works, it's just a bit slow at that size. It's not great, but ... usable to me? I used Sonnet 4.0 over api for half a year or so before, after all.
Only way to know if your own criteria are now matched -or not yet- is to test it for yourself with your own benchmark or what have you.
And it does show a promising direction going forward: usable (to some) local models becoming efficient enough to run on consumer hardware.
[1] released mid-2025
[2] take with salt - only tests personal usability
+ Note that some benchmarks do show Qwen3.5-35B-A3B matching Sonnet 4.5 (released later last year); but I treat those with the same skepticism you do , clearly ;)
Re: Claude may require identity verification in some cases
#70In the old USSR one had to register a typewriter. Sweet memories. And at that time western people (deservedly) laughed at it or used facts like this to show how backwards the country was
It's okay when corporation does it...
And the corporation is free to sell all that data straight to the government the second after collecting it. The communists just screwed up trying to do all the authoritarianism by themselves.