Hacker News
- DeepSeek-V3 runs at 20 tokens/s on Mac Studio, and that's a nightmare for OpenAI https://venturebeat.com/ai/deepseek-v3-now-runs-at-20-tokens-per-second-on-mac-studio-and-thats-a-nightmare-for-openai/ 2 comments
Linked pages
- Apple reveals M3 Ultra, taking Apple silicon to a new extreme - Apple https://www.apple.com/newsroom/2025/03/apple-reveals-m3-ultra-taking-apple-silicon-to-a-new-extreme/ 1341 comments
- Mac Studio - Apple https://www.apple.com/mac-studio/ 842 comments
- Introducing Claude 3.5 Sonnet \ Anthropic https://www.anthropic.com/news/claude-3-5-sonnet 289 comments
- OpenAI https://openai.com/ 136 comments
- [2404.19737] Better & Faster Large Language Models via Multi-token Prediction https://arxiv.org/abs/2404.19737 132 comments
- DeepSeek https://www.deepseek.com/ 98 comments
- Home \ Anthropic https://www.anthropic.com/ 48 comments
- Alibaba launches over 100 new AI models, releases text-to-video generation https://www.cnbc.com/2024/09/19/alibaba-launches-over-100-new-ai-models-releases-text-to-video-generation.html 33 comments
- deepseek-ai/DeepSeek-R1 · Hugging Face https://huggingface.co/deepseek-ai/DeepSeek-R1 6 comments
- OpenRouter https://openrouter.ai 5 comments
- deepseek-ai/DeepSeek-V3-0324 https://simonwillison.net/2025/Mar/24/deepseek/ 5 comments
- https://openai.com/o1/ 3 comments
- Mixture of Experts Explained https://huggingface.co/blog/moe 2 comments
- deepseek-ai/DeepSeek-V3-0324 · Hugging Face https://huggingface.co/deepseek-ai/DeepSeek-V3-0324 2 comments
- [2405.04434] DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model https://arxiv.org/abs/2405.04434 0 comments
- deepseek-ai/DeepSeek-V3-0324 at main https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/tree/main 0 comments
Related searches:
Search whole site: site:venturebeat.com
Search title: DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that's a nightmare for OpenAI | VentureBeat
See how to search.