Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

pretty-radio-b75.notion.site

Post reply on HN
Print view View original

1–7 of 7 posts

Re: DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

#3

Post by sijuntan »

Through a joint collaboration between the Agentica team and Together AI, we release DeepCoder-14B-Preview, a code reasoning model finetuned from Deepseek-R1-Distilled-Qwen-14B via distributed RL. It achieves an impressive 60.6% Pass@1 accuracy on LiveCodeBench (+8% improvement), matching the performance of o3-mini-2025-01-031 (Low) and o1-2024-12-17 with just 14B parameters. We’ve open-sourced our dataset, code, training logs, and systems optimizations for everyone to progress on scaling and accelerating intelligence with RL.

Re: DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

#4

Post by daemonologist »

apothegm wrote: post #2

What sort of hardware is needed to run a model like this at a vaguely useful speed?

Depends on what you consider vaguely useful, but any modern GPU which can fit the weights at a reasonable quantization (so, 16+ GB, maybe 12 in a pinch) will probably be tolerable. Bare minimum is probably ~3060 12GB.

Re: DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

#5

Post by apothegm »

daemonologist wrote: post #4
apothegm wrote: post #2

What sort of hardware is needed to run a model like this at a vaguely useful speed?

Depends on what you consider vaguely useful, but any modern GPU which can fit the weights at a reasonable quantization (so, 16+ GB, maybe 12 in a pinch) will probably be tolerable. Bare minimum is probably ~3060 12GB.

Thanks! So this could actually be worth running on a mid-specced recentish Mac laptop?

Re: DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

#6

Post by daemonologist »

apothegm wrote: post #5
daemonologist wrote: post #4

Earlier quoted context omitted.

Depends on what you consider vaguely useful, but any modern GPU which can fit the weights at a reasonable quantization (so, 16+ GB, maybe 12 in a pinch) will probably be tolerable. Bare minimum is probably ~3060 12GB.

Thanks! So this could actually be worth running on a mid-specced recentish Mac laptop?

Macs are a bit odd because you're using system memory (so, more but slower) and Apple's APIs, but it's definitely worth a try. I'd guess >= M2 Pro + >= 24 GB RAM would do okay. Also maybe try an MLX version? (e.g. https://huggingface.co/justinmeans/DeepCoder-14B-Preview-mlx...)

Re: DeepCoder: An Fully Open-Source 14B Coder at O3-Mini Level

#7

Post by apothegm »

daemonologist wrote: post #6
apothegm wrote: post #5

Earlier quoted context omitted.

Thanks! So this could actually be worth running on a mid-specced recentish Mac laptop?

Macs are a bit odd because you're using system memory (so, more but slower) and Apple's APIs, but it's definitely worth a try. I'd guess >= M2 Pro + >= 24 GB RAM would do okay. Also maybe try an MLX version? (e.g. https://huggingface.co/justinmeans/DeepCoder-14B-Preview-mlx... )

Sweet. Thank you so much!
Post reply on HN