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

DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

artificialanalysis.ai

Post reply on HN
Print view View original

191–200 of 342 posts

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#191

Post by FuckButtons »

vmt-man wrote: post #93
kamranjon wrote: post #65

Earlier quoted context omitted.

Can't wait for the DwarfStar quants - I have been using DeepSeek v4 flash (preview) as my main coding agent for months now (running on my 128gb mbp) - it seems this model outperforms GLM 5.2 on nearly every metric. Thanks for sharing the news, I was refreshing huggingface but gave up thinking it likely would take some more time.

are you working in earplugs? :)) even with 128 gigs of ram it must be super noisy.

There’s fan noise, but the acoustic engineers at Apple have done a very good job of making it be pretty much not noticeable to someone who has noise sensitivity (me).

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#192

Post by knuppar »

kamranjon wrote: post #65
coder543 wrote: post #41

The weights were just released a few minutes ago: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

Can't wait for the DwarfStar quants - I have been using DeepSeek v4 flash (preview) as my main coding agent for months now (running on my 128gb mbp) - it seems this model outperforms GLM 5.2 on nearly every metric. Thanks for sharing the news, I was refreshing huggingface but gave up thinking it likely would take some more time.

same. been running it in a dgx spark and it slaps

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#193

Post by bwfan123 »

L8D wrote: post #182
bwfan123 wrote: post #165

> For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework So, are they planning to announce an optimized coding agent harness as well ? DSv4 flash is a fantastic model, and my daily driver. With reasonix or pi, I can code all day long and pay a few pennies for it. No token anxiety. Whereas the sam…

If you're not paying for the model through Open router, then which provider are you buying it from? I thought that if that provider was listed on open router it would be the same price as going directly to the provider? Are you buying from a provider that isn't listed on open router already?

> Are you buying from a provider that isn't listed on open router already

I am using openrouter with zdr guardrail which routes to any provider that supposedly doesnt train on user data. I also use fireworks (directly, not via openrouter) which is a provider promising zdr and has a bunch of open weights models. My issue is that these zdr providers dont transparently disclose caching/tokens etc and so they end up being far more expensive than directly using DS.

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#194

Post by rupx »

jvuygbbkuurx wrote: post #109
0cf8612b2e1e wrote: post #106

Somewhat relatedly, how do the economics for Huggingface work? They must be hosting petabytes of models and datasets by now. I have downloaded quite a few “just in case”, only to replace them with the later iteration months later. Does the file hosting actually cost peanuts when you do it yourself and the cloud has shattered my understanding of what it actually costs to deliver so much data?

Maybe download numbers are relatively low

Download numbers are reported on the site, and they aren't low.

CDN costs are pennies compared to inference and training though, HuggingFace will just get another 100 million and be set.

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#195

Post by himata4113 »

lima wrote: post #123
0cf8612b2e1e wrote: post #106

Somewhat relatedly, how do the economics for Huggingface work? They must be hosting petabytes of models and datasets by now. I have downloaded quite a few “just in case”, only to replace them with the later iteration months later. Does the file hosting actually cost peanuts when you do it yourself and the cloud has shattered my understanding of what it actually costs to deliver so much data?

Bandwidth is really cheap when you run your own infra

It's not only cheap, it's actually free since if you are not using your 95th percentile you are losing money.

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#197

Post by refulgentis »

baalimago wrote: post #15

New Deepseek models are like Christmas for me. Really big fan of low cost API models, noone does it better than DS. Until VRAM price is low enough to run models locally, this is the way to go. The subsidized subscription model won't last, API pricing "feels" closer to a true sustainable business model.

FWIW, looking at pricing myself, it needs to 5x the tokens to get the same results as GPT 5.6 Luna at a much lower TPS. (doesn't obviate the fact that the pressure causes incumbents to push and push to optimize, thank you Deepseek!)

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#198

Post by tough »

kamranjon wrote: post #65
coder543 wrote: post #41

The weights were just released a few minutes ago: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

Can't wait for the DwarfStar quants - I have been using DeepSeek v4 flash (preview) as my main coding agent for months now (running on my 128gb mbp) - it seems this model outperforms GLM 5.2 on nearly every metric. Thanks for sharing the news, I was refreshing huggingface but gave up thinking it likely would take some more time.

I've put Opus to it and it says it will take 3-4h to do the process to the new weights. hoping it works!

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#199

Post by ycui7 »

kamranjon wrote: post #65
coder543 wrote: post #41

The weights were just released a few minutes ago: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

Can't wait for the DwarfStar quants - I have been using DeepSeek v4 flash (preview) as my main coding agent for months now (running on my 128gb mbp) - it seems this model outperforms GLM 5.2 on nearly every metric. Thanks for sharing the news, I was refreshing huggingface but gave up thinking it likely would take some more time.

you don’t need new weight. try vllm-moet from github. it will autogenerate 2-bit plane.

Re: DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis

#200

Post by nodja »

VulgarExigency wrote: post #55
baalimago wrote: post #15

New Deepseek models are like Christmas for me. Really big fan of low cost API models, noone does it better than DS. Until VRAM price is low enough to run models locally, this is the way to go. The subsidized subscription model won't last, API pricing "feels" closer to a true sustainable business model.

I would bet that Deepseek API pricing is still more cost effective per token than the subscriptions. With the increase in quality Deepseek Flash just got (in my personal testing so far, it seems to have improved a lot at following instructions, and has become more proactive), there really isn’t anything that can match it in terms of cost effectiveness.

I'm not a heavy user of agentic coding, but still use them quite a bit for some automation here and there. I've been going around shopping all the ~$10 subscriptions and I finally settled on openrouter + ds4 pro. The more intensive days cost me $1 and I set a $2 weekly limit which I've never hit the past 3 weeks, to me it's way cheaper than most subscriptions and I don't have to worry about maximizing my weekly quota/resets.
Post reply on HN