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.
The link is off. This link works https://api-docs.deepseek.com/updates#deepseek-v31-terminus
Notable performance improvement in agentic tool use: https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus
I see no article in the link, just "news250922" header with some layout
It’s up again, check it.
Twitter/X post link: https://twitter.com/deepseek_ai/status/1970117808035074215
Also Hugging Face model link: https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus
> 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?
They seem fairly competitive with each other. You would have to benchmark them for your specific use case.
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.
MIT license that lets you run it on your own hardware and make money off of it.