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

DeepSeek-v3.1

api-docs.deepseek.com

Post reply on HN
Print view View original

51–60 of 273 posts

Re: DeepSeek-v3.1

#51

Post by rapind »

imranq wrote: post #42
abtinf wrote: post #25

Unrelated, but it would really be nice to have a chart breaking down Price Per Token Per Second for various model, prompt, and hardware combinations.

There is one: https://pricepertoken.com/

Claude's Opus pricing is nuts. I'd be surprised if anyone uses it without the top max subscription.

Re: DeepSeek-v3.1

#52

Post by jamiek88 »

tehjoker wrote: post #43
simianparrot wrote: post #32

Earlier quoted context omitted.

[flagged]

Incredible how "keeping their people down" means leaps in personal wealth and happiness for huge swathes of the population and internal criticism is that it is a "poverty reduction machine" that is too focused.

Tell that to the Uyghurs if you can get into their concentration camp to have a chat.

Re: DeepSeek-v3.1

#53

Post by jaggs »

jamiek88 wrote: post #52
tehjoker wrote: post #43

Earlier quoted context omitted.

Incredible how "keeping their people down" means leaps in personal wealth and happiness for huge swathes of the population and internal criticism is that it is a "poverty reduction machine" that is too focused.

Tell that to the Uyghurs if you can get into their concentration camp to have a chat.

Yep, comment arrives right on time. Nicely played. :)

Re: DeepSeek-v3.1

#54

Post by wkat4242 »

amelius wrote: post #50
guluarte wrote: post #17

Earlier quoted context omitted.

tbh companies like anthopic, openai, create custom agents for specific benchmarks

Aren't good benchmarks supposed to be secret?

This industry is currently burning billions a month. With that much money around I don't think any secrets can exist.

Re: DeepSeek-v3.1

#55

Post by dr_dshiv »

sync wrote: post #49
amrrs wrote: post #9

Earlier quoted context omitted.

Any example or prompt you use to make this statment?

I'm doing coreference resolution and this model (w/o thinking) performs at the Gemini 2.5-Pro level (w/ thinking_budget set to -1) at a fraction of the cost.

Strong claim there!

Re: DeepSeek-v3.1

#57

Post by indigodaddy »

bigyabai wrote: post #6
esafak wrote: post #5

It seems behind Qwen3 235B 2507 Reasoning (which I like) and gpt-oss-120B: https://artificialanalysis.ai/models/deepseek-v3-1-reasoning Pricing: https://openrouter.ai/deepseek/deepseek-chat-v3.1

Those Qwen3 2507 models are the local creme-de-la-creme right now. If you've got any sort of GPU and ~32gb of RAM to play with, the A3B one is great for pair-programming tasks.

Do we get these good qwen models when using qwen-code CLI tool and authing via qwen.ai account?

Re: DeepSeek-v3.1

#59

Post by aussieguy1234 »

They say the SWE bench verified score is 66%. Claude Sonnet 4 is 67%. Not sure if the 1% difference here is statistically significant or not.

I'll have to see how things go with this model after a week, once the hype has died down.

Re: DeepSeek-v3.1

#60

Post by pshirshov »

danielhanchen wrote: post #39

For local runs, I made some GGUFs! You need around RAM + VRAM >= 250GB for good perf for dynamic 2bit (2bit MoE, 6-8bit rest) - can also do SSD offloading but it'll be slow. ./llama.cpp/llama-cli -hf unsloth/DeepSeek-V3.1-GGUF:UD-Q2_K_XL -ngl 99 --jinja -ot ".ffn_.*_exps.=CPU" More details on running + optimal params here: https://docs.unsloth.ai/basics/deepseek-v3.1

By the way, I'm wondering why unsloth (a goddamn python library) tries to run apt-get with sudo (and fails on my nixos). Like how tf we are supposed to use that?
Post reply on HN