Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Downloaded the 14B, 32B, and 70B variants to my Ollama instance. All three are very impressive, subjectively much more capable than QwQ. 70B especially, unsurprisingly. Gave it some coding problems, even 14B did a pretty good job. I wish I could collapse the "thinking" section in Open-WebUI, and also the title for the chat is currently generated wrong - the same model is used by default as for generation, so the title begins with "<thinking>". Be that as it may, I think these will be the first "locally usable" reasoning models for me. URL for the checkpoints: https://ollama.com/library/deepseek-r1


Thanks for sharing your experience with the 14B, 32B, and 70B variants! I'm curious, what hardware setup are you using to run these models on your Ollama instance?


I don't think asking coding problems to a model by itself is fair. Almost all commercial models are combining a RAG and web-search. I find that most correct answers come from that, not from the actual model.


Coding problems are never solved with rag.


%90 of the time all the LLM does is to point me to the website where the solution is.


well this is not how normally coding models used anyway.


Librechat handled artifact like sections better than openwebui so suspect it’ll have support to collapse it first

Feels much heavier/slower as an app though




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: