wirybeige

I have noticed it to be slightly worse, mostly on "bad" sites. Just using Brave at this point though.

Granite is IBM

I presume the providers are the ones giving the info to OpenRouter? I mean, technically it is a mix of fp8 and fp4 (although it is predominately fp4), so I don't think either is inaccurate.

DS4 Pro/Flash were post trained with QAT, so they are already quantized to FP4 for the most part. That's why when downloading the weights, they are much smaller than what their weights at fp8 or fp16 would be. For example, Flash is a 284B model, but its GB size is only ~160GB. OFC maybe DeeppInfra went even further, but there is no proof of that.

Personal anecdote --- Proton Pass very quickly went from worse than Bitwarden to better with more reliable auto-fill.

These were trained on NVIDIA gpus. It is running inference on Huawei.

Why would these 3rd-party providers be taking losses? Together, Novita, etc... are not losing money on inference services, they are profiting. You can easily do napkin math with current & last gen Nvidia cards to calculate cost to host/serve these models. I would also doubt that any 1st-party providers like OpenAI and Anthropic lose money on per token billing. There is almost undoubtedly healthy margin being made on that.

Pricing for DeepSeek V4 flash is $0.14 in/$0.28 out across basically every provider or close to it. It seems most providers just follow the model creator and set their prices to match. V4 pro was set to be $1.74 in/$3.48 out when DeepSeek first announced it; all providers have set their prices to be about that price, & now DeepSeek has set their pricing to $0.435 in/ $0.87 out. I don't know if this is special pricing, or the promise they made for dropping the price when they get more Huawei cards online. It seems that providers like ParaSail, Together, and Novita just set the price when the model comes out and don't compete.

The vulkan backend for llama.cpp isn't that far behind rocm for pp and tp speeds

Sodium batteries don't yet have the scale that lifepo4 batteries have. I'd expect we will see them get cheaper.

HDR playback in chrome on KDE works as expected from what I can tell. For GNOME 49.2 it does not, it doesn't get the luminance that it should at this time. 49.3 may fix this.

Sorry it doesn't work for you. I don't have that issue. Gnome looks proper in HDR mode for both HDR and SDR content for me.