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

DeepSeek v4

api-docs.deepseek.com

Post reply on HN
Print view View original

81–90 of 1001 posts

Re: DeepSeek v4

#81

Post by snovv_crash »

rvz wrote: post #36
onchainintel wrote: post #17

Earlier quoted context omitted.

How does it compare to Opus 4.7? I've been immersed in 4.7 all week participating in the Anthropic Opus 4.7 hackathon and it's pretty impressive even if it's ravenous from a token perspective compared to 4.6

It is more than good enough and has effectively caught up with Opus 4.6 and GPT 5.4 according to the benchmarks. It's about 2 months behind GPT 5.5 and Opus 4.7. As long as it is cheap to run for the hosting providers and it is frontier level, it is a very competitive model and impressive against the others. I give it 2 years maximum for consumer hardware to run models that are 500B - 800B quantized on their machines…

With the ability of the Qwen3.6 27B, I think in 2 years consumers will be running models of this capability on current hardware.

Re: DeepSeek v4

#84

Post by DiscourseFan »

ehnto wrote: post #75
wordpad wrote: post #16

Earlier quoted context omitted.

The players barely ever change. People don't have problems following sports, you shouldn't struggle so much with this once you accept top spot changes.

It is funny seeing people ping pong between Anthropic and ChatGPT, with similar rhetoric in both directions. At this point I would just pick the one who's "ethics" and user experience you prefer. The difference in performance between these releases has had no impact on the meaningful work one can do with them, unless perhaps they are on the fringes in some domain. Personally I am trying out the open models cloud host…

I find ChatGPT annoying mostly

Re: DeepSeek v4

#85

Post by simonw »

inventor7777 wrote: post #57
ls612 wrote: post #28

How long does it usually take for folks to make smaller distills of these models? I really want to see how this will do when brought down to a size that will run on a Macbook.

Weren't there some frameworks recently released to allow Macs to stream weights from fast SSDs and thus fit way more parameters than what would normally fit in RAM? I have never tried one yet but I am considering trying that for a medium sized model.

I've been calling that the "streaming experts" trick, the key idea is to take advantage of Mixture of Expert models where only a subset of the weights are used for each round of calculations, then load those weights from SSD into RAM for each round.

As I understand it if DeepSeek v4 Pro is a 1.6T, 49B active that means you'd need just 49B in memory, so ~100GB at 16 bit or ~50GB at 8bit quantized.

v4 Flash is 284B, 13B active so might even fit in <32GB.

Re: DeepSeek v4

#86

Post by ycui1986 »

simonw wrote: post #63

I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…

I really like the pro version. The pelican is so cute.

Re: DeepSeek v4

#89

Post by awakeasleep »

DiscourseFan wrote: post #84
ehnto wrote: post #75

Earlier quoted context omitted.

It is funny seeing people ping pong between Anthropic and ChatGPT, with similar rhetoric in both directions. At this point I would just pick the one who's "ethics" and user experience you prefer. The difference in performance between these releases has had no impact on the meaningful work one can do with them, unless perhaps they are on the fringes in some domain. Personally I am trying out the open models cloud host…

I find ChatGPT annoying mostly

Open settings > personalization. Set it to efficient base style. Turn off enthusiasm and warmth. You’re welcome

Re: DeepSeek v4

#90

Post by inventor7777 »

simonw wrote: post #85
inventor7777 wrote: post #57

Earlier quoted context omitted.

Weren't there some frameworks recently released to allow Macs to stream weights from fast SSDs and thus fit way more parameters than what would normally fit in RAM? I have never tried one yet but I am considering trying that for a medium sized model.

I've been calling that the "streaming experts" trick, the key idea is to take advantage of Mixture of Expert models where only a subset of the weights are used for each round of calculations, then load those weights from SSD into RAM for each round. As I understand it if DeepSeek v4 Pro is a 1.6T, 49B active that means you'd need just 49B in memory, so ~100GB at 16 bit or ~50GB at 8bit quantized. v4 Flash is 284B, 13…

Ahh, that actually makes more sense now. (As you can tell, I just skimmed through the READMEs and starred "for later".)

My Mac can fit almost 70B (Q3_K_M) in memory at once, so I really need to try this out soon at maybe Q5-ish.

Post reply on HN