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 1 year 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

[-] yogthos@lemmygrad.ml 3 points 1 year ago

I got DeepSeek running on ollama https://dev.to/shayy/run-deepseek-locally-on-your-laptop-37hl

but for language practice I'm just using this app https://www.superchinese.com/

[-] bennieandthez@lemmygrad.ml 3 points 1 year ago

awesome thanks

[-] juchenecromancer@lemmygrad.ml 1 points 1 year ago

What kind of specs do you need to run DeepSeek locally? A few months back, I tried using ollama to run some small llama models on my home laptop (Ubuntu with 16GB RAM and a weak Nvidia integrated GPU w/ nouveau drivers) at it was borderline unusable.

[-] yogthos@lemmygrad.ml 1 points 1 year ago

I got the deepseek-r1:14b-qwen-distill-fp16 version running with 32gb ram and a GPU here.

this post was submitted on 24 Jan 2025

44 points (97.8% liked)

Technology

1379 readers

22 users here now

A tech news sub for communists

founded 3 years ago

MODERATORS

muad_dibber@lemmygrad.ml

burlemarx@lemmygrad.ml

egs81t@lemmygrad.ml