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

161–170 of 1001 posts

Re: DeepSeek v4

#161

Post by zozbot234 »

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.

These are more like experiments than a polished release as of yet. And the reduction in throughput is high compared to having the weights in RAM at all times, since you're bottlenecked by the SSD which even at its fastest is much slower than RAM.

Re: DeepSeek v4

#162

Post by bl4ckneon »

necovek wrote: post #43
fblp wrote: post #13

There's something heartwarming about the developer docs being released before the flashy press release.

Where's the training data and training scripts since you are calling this open source ? Edit: it seems "open source" was edited out of the parent comment.

Aww yes, let me push a couple petabytes to my git repo for everyone to download...

Re: DeepSeek v4

#163

Post by necovek »

b65e8bee43c2ed0 wrote: post #109
necovek wrote: post #43

Earlier quoted context omitted.

Where's the training data and training scripts since you are calling this open source ? Edit: it seems "open source" was edited out of the parent comment.

doesn't it get tiring after a while? using the same (perceived) gotcha, over and over again, for three years now? no one is ever going to release their training data because it contains every copyrighted work in existence. everyone, even the hecking-wholesome safety-first Anthropic, is using copyrighted data without permission to train their models. there you go.

There is an easy fix already in widespread use: "open weights".

It is very much a valuable thing already, no need to taint it with wrong promise.

Though I disagree about being used if it was indeed open source: I might not do it inside my home lab today, but at least Qwen and DeepSeek would use and build on what eg. Facebook was doing with Llama, and they might be pushing the open weights model frontier forward faster.

Re: DeepSeek v4

#164

Post by bokkies »

doctoboggan wrote: post #21
nthypes wrote: post #5

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.

Is it honestly better than Opus 4.6 or just benchmaxxed? Have you done any coding with an agent harness using it? If its coding abilities are better than Claude Code with Opus 4.6 then I will definitely be switching to this model.

Apparently glm5.1 and qwen coder latest is as good as opus 4.6 on benchmarks. So I tried both seriously for a week (glm Pro using CC) and qwen using qwen companion. Thought I could save $80 a month. Unfortunately after 2 days I had switched back to Max. The speed (slower on both although qwen is much faster) and errors (stupid layout mistakes, inserting 2 footers then refusing to remove one, not seeing obvious problems in screenshots & major f-ups of functionality), not being able to view URLs properly, etc. I'll give deepseek a go but I suspect it will be similar. The model is only half the story. Also been testing gpt5.4 with codex and it is very almost as good as CC... better on long running tasks running in background. Not keen on ChatGPT codex 'personality' so will stick to CC for the most part.

Re: DeepSeek v4

#166

Post by necovek »

bl4ckneon wrote: post #162
necovek wrote: post #43

Earlier quoted context omitted.

Where's the training data and training scripts since you are calling this open source ? Edit: it seems "open source" was edited out of the parent comment.

Aww yes, let me push a couple petabytes to my git repo for everyone to download...

An easier thing would be to say "open weights", yes.

Re: DeepSeek v4

#167

Post by fractalf »

rohanm93 wrote: post #153

This is shockingly cheap for a near frontier model. This is insane. For context, for an agent we're working on, we're using 5-mini, which is $2/1m tokens. This is $0.30/1m tokens. And it's Opus 4.6 level - this can't be real. I am uncomfortable about sending user data which may contain PII to their servers in China so I won't be using this as appealing as it sounds. I need this to come to a US-hosted environment at a…

Right now Im much more worried about sending data to the US and A.. At least theres a less chanse it will be missused against -me-

Re: DeepSeek v4

#168

Post by EnPissant »

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:…

This should not be the top comment on every model release post. It's getting tiring.

Re: DeepSeek v4

#169

Post by redrove »

zargon wrote: post #142
revolvingthrow wrote: post #119

Earlier quoted context omitted.

For flash? 4 bit quant, 2x 96GB gpu (fast and expensive) or 1x 96GB gpu + 128GB ram (still expensive but probably usable, if you’re patient). A mac with 256 GB memory would run it but be very slow, and so would be a 256GB ram + cheapo GPU desktop, unless you leave it running overnight. The big model? Forget it, not this decade. You can theoretically load from SSD but waiting for the reply will be a religious experien…

Flash is less than 160 GB. No need to quantize to fit in 2x 96 GB. Not sure how much context fits in 30 GB, but it should be a good amount.

It seems to be 160GB at mixed FP4+FP8 precision, FYI. Full FP8 is 250GB+. (B)F16 at around double I would assume.
Post reply on HN