Friedrich Marty

did u understand how to actually retrieve all the tools?
I'm trying to build an MCP Client (the one interacting with the servers) and found that simply initializing it with the jsonrpc doesn't actually return the tools. I have to pass "tools/list" as the method and then it returns the tools... but they are not separated into "resources", "tools" and "prompts" or whatever... i cant get the prompts at all in fact!
not even "prompts/list" works in the jsonrpc....

Where do u have that info about qwen 3 from? I'm really curious now...

maybe i am not understanding this correctly, but in the picture you say that you menaged to squeeze the model to a size of 34GB, but then you say that now it can run on GPUs with "just" 24 GB of VRAM.

Was this a typo or am I maybe missing something here?

This really comes down to what type of robots.

• Are we talking lil hobbyist robots, about 20-30 centimeters?

or are we talking

• larger human-sized robots with figure-2 level movement options?

for a smol hobbyist one, I'd be able to pay anything sub 300€, if it's also open-hardware that is (if something breaks, we can replace it).

For a big, human-sized robot, the pricing is more difficult. I would pay anything up to 5000€, even though I'm currently unable to.

I believe it would make most sense to compute all the AI stuff over the network and not inside the bot (better for weight and battery life).

If this is real, I'd be super excited either way.