What's the catch?

edit: I seem to be the only one excited by the possibilities of such small yet powerful models. This is an iPhone moment: a computer that fits in your pocket, except this time it's smart.

> Gemma 3n models are listed with parameter counts, such as E2B and E4B, that are lower than the total number of parameters contained in the models. The E prefix indicates these models can operate with a reduced set of Effective parameters. This reduced parameter operation can be achieved using the flexible parameter technology built into Gemma 3n models to help them run efficiently on lower resource devices.

> The parameters in Gemma 3n models are divided into 4 main groups: text, visual, audio, and per-layer embedding (PLE) parameters. With standard execution of the E2B model, over 5 billion parameters are loaded when executing the model. However, using parameter skipping and PLE caching techniques, this model can be operated with an effective memory load of just under 2 billion (1.91B) parameters, as illustrated in Figure 1.

> Gemma 3n leverages a Google DeepMind innovation called Per-Layer Embeddings (PLE) that delivers a significant reduction in RAM usage.

Like you I’m also interested in the architectural details. We can speculate but we’ll probably need to wait for some sort of paper to get the details.

[1] https://arxiv.org/pdf/2310.07707

At a very high level, instead of having embeddings at the input layers, this method keeps the embeddings at the layer level. That is every transformer layer would have its own set of learnable embedding vectors that are used to modify the processed hidden states flowing through the network. Mostly, the embeddings are precomputed and stored separately. They are queried at inference time and has very low latency, so you can get comparable performance with half the RAM. (i am not exactly sure how 3n is doing it, but talking it in a general sense).

Though, I won't be surprised if they try to force devs to use their models for "privacy" (and not monopolistic reasons, of course).

I've also seemingly hit a rate limit on Gemini Pro 2.5 (on an account not subscribed to Gemini Advanced) yesterday, even though my last query is weeks past.

Possibly there's a capacity shortage (I'd presume it all runs on the same Google hardware in the end), and they are prioritizing paid inference?

Also:

> These models were evaluated at full precision (float32)

For 4B effective parameters that's 16 GB ram.

Hint: You have to set the Max tokens to 32000 for longer conversations. The slider makes it look like it's limited to 1024, just enter it manually.