11–20 of 30 posts
> What’s improved? Language consistency: fewer CN/EN mix-ups & no more random chars. It's good that they made this improvement. But is there any advantages at this point using DeepSeek over Qwen?
MIT license that lets you run it on your own hardware and make money off of it.
> What’s improved? Language consistency: fewer CN/EN mix-ups & no more random chars. It's good that they made this improvement. But is there any advantages at this point using DeepSeek over Qwen?
> What’s improved? Language consistency: fewer CN/EN mix-ups & no more random chars. It's good that they made this improvement. But is there any advantages at this point using DeepSeek over Qwen?
I wish there was some easy resource to keep up with the latest models. The best I have come up with so far is asking one model to research the others. Realistically I want to know latest versions, best use case, performance (in terms of speed) relative to some baseline, and hardware requirements to run it.
Earlier quoted context omitted.
I wish there was some easy resource to keep up with the latest models. The best I have come up with so far is asking one model to research the others. Realistically I want to know latest versions, best use case, performance (in terms of speed) relative to some baseline, and hardware requirements to run it.
have you tried https://artificialanalysis.ai/
Earlier quoted context omitted.
have you tried https://artificialanalysis.ai/
Dumb collation of benchmarks that the big labs are essentially training on. Livebench.ai is the industry standard - non contaminated, new questions every few months.
sure would be neat if these companies would release models that could run on consumer hardware
1) We haven't managed to distill models enough to get good enough performance to fit in the typical gaming desktop (say, 7B-24b class models). Even then though - most consumers don't have high end desktops, so even a 3060 class GPU requirement would exclude a lot of people.
2) Nothing is stopping you/anyone from buying 24ish 5090s (a consumer hardware product) to get the required ~600GB-1TB of VRAM to run unquantized deepseek except time/money/know how. Sure, it's unreasonably expensive but it's not like labs are conspiring to prevent people from running these models, it's just expensive for everyone and the common person doesn't have the funding to get into it.
sure would be neat if these companies would release models that could run on consumer hardware
https://huggingface.co/mlx-community/Qwen3-Next-80B-A3B-Inst...