How can you reasonably try to get near frontier (even at all tps) on hardware you own? Maybe under 5k in cost?
DeepSeek v4
61–70 of 1001 posts
Re: DeepSeek v4
#62congrats
Re: DeepSeek v4
#63I 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: https://simonwillison.net/2025/Mar/24/deepseek/
Re: DeepSeek v4
#64How 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.
Do you have the links for those? Very interested
Re: DeepSeek v4
#65Which version fits in a Mac Studio M3 Ultra 512 GB?
The Flash one should - it's 160GB on Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/tree/ma...
Re: DeepSeek v4
#66https://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.
> (better than Opus 4.6)
There we go again :) It seems we have a release each day claiming that. What's weird is that even deepseek doesn't claim it's better than opus w/ thinking. No idea why you'd say that but anyway.
Dsv3 was a good model. Not benchmaxxed at all, it was pretty stable where it was. Did well on tasks that were ood for benchmarks, even if it was behind SotA.
This seems to be similar. Behind SotA, but not by much, and at a much lower price. The big one is being served (by ds themselves now, more providers will come and we'll see the median price) at 1.74$ in / 3.48$ out / 0.14$ cache. Really cheap for what it offers.
The small one is at 0.14$ in / 0.28$ out / 0.028$ cache, which is pretty much "too cheap to matter". This will be what people can run realistically "at home", and should be a contender for things like haiku/gemini-flash, if it can deliver at those levels.
Re: DeepSeek v4
#67I 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:…
No way. The Pro pelican is fatter, has a customized front fork, and the sun is shining! He’s definitely living the best life.
Re: DeepSeek v4
#68How 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.
Unsloth often turn them around within a few hours, they might have gone to bed already though!
Keep an eye on https://huggingface.co/unsloth/models
Update ten minutes later: https://huggingface.co/unsloth/DeepSeek-V4-Pro just appeared but doesn't have files in yet, so they are clearly awake and pushing updates.
Re: DeepSeek v4
#69Truly open source coming from China. This is heartwarming. I know if the potential ulterior motives.
Open weight!
Re: DeepSeek v4
#70https://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.
I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits.
As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same results. I have a feeling we might all be getting swindled by the whole AI industry with benchmarks that just make it look like everything's improving.