DeepSeek's free 685B-parameter AI model runs at 20 tokens/second on Apple's Mac Studio, outperforming Claude Sonnet while using just 200 watts, challenging OpenAI's cloud-dependent business model.
You must log in or register to comment.
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community’s icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
- 0 users online
- 13 users / day
- 237 users / week
- 638 users / month
- 1.28K users / 6 months
- 1 subscriber
- 1.67K Posts
- 28.1K Comments
- Modlog
Turns out when you build your entire business on copyright infringement, a. it’s easy to steal your business and b. you have no recourse when someone does.
Sometimes I am happy to be able to say that I am not surprised by a piece of news and for once it does not mean in a political terror/economic destruction/environmental eradication way.
Deepseek is an absolutely massive model, it’s not the one people will be running. Rather, look at qwen/qwq, gemma and a number of other smaller ones
No, people who want something approaching chatgpt but local want to run at least deepseek V3 32B.
Qwen at least fares much worse for my usage as do deepseek V3 under 32B.
The hell is v3 32b. Are you talking about a distill
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
Okay, can somebody who knows about this stuff please explain what the hell a “token per second” means?
A bit like a syllable when you are talking about text based responses. 20 tokens a second is faster than most people could read the output so that’s sufficient for a real time feeling “chat”.
Didn’t a Google engineer put out a white paper about this around the time Facebook’s original LLM weights leaked? They compared the rate of development of corporate AI groups to the open source community and found there was no possible way the corporate model could keep up if there were even a small investment in the open development model. The open source community was solving in weeks open problems the big companies couldn’t solve in years. I guess China was paying attention.
China “open sources” a lot of their technologies. They treat it as a form of competition, we’ll show you how to do x but you show us how to do u and whoever is better at both wins out, there’s a lot of short videos on how BYD taught other Chinese EV manufacturers and even Ford how their automated manufacturing plants work. The end result, everything becomes a highly optimized process. Glad to see they’re also adopting this framework with open sourcing AI development.
This is also a reason why there’s a hugeee cultural clash with US IP theft.