Technology

1009 readers

71 users here now

A tech news sub for communists

founded 2 years ago

MODERATORS

ByteDance just dopped Doubao-1.5-pro tht uses sparse MoE architecture, it matches GPT 4o benchmarks while being 50x cheaper to run, and it's 5x cheaper than DeepSeek (www.aibase.com)

submitted 3 days ago by yogthos@lemmygrad.ml to c/technology@lemmygrad.ml

23 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] poo_22@lemmygrad.ml 2 points 2 days ago (1 children)

According to this page to run the full model you need about 1.4TB of memory, or about 16 A100 GPUs. Which is still prohibitively expensive for an individual enthusiast, but yes you can run a simplified model locally with ollama. Still probably needs a GPU with a lot of memory.

[–] yogthos@lemmygrad.ml 2 points 2 days ago

I got deepseek-r1:14b-qwen-distill-fp16 running locally with 32gb ram and a GPU, but yeah you do need a fairly beefy machine to run even medium sized models.