41–50 of 485 posts
Well props to them for continuing to improve, winning on cost-effectiveness, and continuing to publicly share their improvements. Hard not to root for them as a force to prevent an AI corporate monopoly/duopoly.
I genuinely do not understand the evaluations of the US AI industry. The chinese models are so close and far cheaper
Two aspects to consider: 1. Chinese models typically focus on text. US and EU models also bear the cross of handling image, often voice and video. Supporting all those is additional training costs not spent on further reasoning, tying one hand in your back to be more generally useful. 2. The gap seems small, because so many benchmarks get saturated so fast. But towards the top, every 1% increase in benchmarks is sign…
The scales are a bit murky here, but if we look at the 'Coding' metric, we see that Kimi K2 outperforms Sonnet 4.5 - that's considered to be the price-perf darling I think even today?
I haven't tried these models, but in general there have been lots of cases where a model performs much worse IRL than the benchmarks would sugges (certain Chinese models and GPT-OSS have been guilty of this in the past)
Earlier quoted context omitted.
Two aspects to consider: 1. Chinese models typically focus on text. US and EU models also bear the cross of handling image, often voice and video. Supporting all those is additional training costs not spent on further reasoning, tying one hand in your back to be more generally useful. 2. The gap seems small, because so many benchmarks get saturated so fast. But towards the top, every 1% increase in benchmarks is sign…
1. Have you seen the Qwen offerings? They have great multi-modality, some even SOTA.
what is the ballpark vram / gpu requirement to run this ?
For just the model itself: 4 x params at F32, 2 x params at F16/BF16, or 1 x params at F8, e.g. 685GB at F8. It will be smaller for quantizations, but I'm not sure how to estimate those. For a Mixture of Experts (MoE) model you only need to have the memory size of a given expert. There will be some swapping out as it figures out which expert to use, or to change expert, but once that expert is loaded it won't be swap…
It's awesome that stuff like this is open source, but even if you have a basement rig with 4 NVIDIA GeForce RTX 5090 graphic cards ($15-20k machine), can it even run with any reasonable context window that isn't like a crawling 10/tps? Frontier models are far exceeding even the most hardcore consumer hobbyist requirements. This is even further
Home rigs like that are no longer cost effective. You're better off buying an rtx pro 6000 outright. This holds both for the sticker price, the supporting hardware price, the electricity cost to run it and cooling the room that you use it in.
Earlier quoted context omitted.
Home rigs like that are no longer cost effective. You're better off buying an rtx pro 6000 outright. This holds both for the sticker price, the supporting hardware price, the electricity cost to run it and cooling the room that you use it in.
Or perhaps a 512GB Mac Studio. 671B Q4 of R1 runs on it.
It's awesome that stuff like this is open source, but even if you have a basement rig with 4 NVIDIA GeForce RTX 5090 graphic cards ($15-20k machine), can it even run with any reasonable context window that isn't like a crawling 10/tps? Frontier models are far exceeding even the most hardcore consumer hobbyist requirements. This is even further
I genuinely do not understand the evaluations of the US AI industry. The chinese models are so close and far cheaper
It's all about the hardware and infrastructure. If you check OpenRouter, no provider offers a SOTA chinese model matching the speed of Claude, GPT or Gemini. The chinese models may benchmark close on paper, but real-world deployment is different. So you either buy your own hardware in order to run a chinese model at 150-200tps or give up an use one of the Big 3. The US labs aren't just selling models, they're selling…
I think GLM 4.6 offered by Cerebras is much faster than any US model.
Earlier quoted context omitted.
Back when deepseek came out and people were tripping over themselves shouting it was so much better than what was out there, it just wasn’t good. It might be this model is super good, I haven’t tried it, but to say the Chinese models are better is just not true. What I really love though is that I can run them (open models) on my own machine. The other day I categorised images locally using Qwen, what a time to be al…
If you thought DeepSeek "just wasn't good," there's a good chance you were running it wrong. For instance, a lot of people thought they were running "DeepSeek" when they were really running some random distillation on ollama.
I genuinely do not understand the evaluations of the US AI industry. The chinese models are so close and far cheaper
Two aspects to consider: 1. Chinese models typically focus on text. US and EU models also bear the cross of handling image, often voice and video. Supporting all those is additional training costs not spent on further reasoning, tying one hand in your back to be more generally useful. 2. The gap seems small, because so many benchmarks get saturated so fast. But towards the top, every 1% increase in benchmarks is sign…