

I think Gufo is optimized only for the Strix Halo but llama.cpp should get you running with expert offloading no problem.


I think Gufo is optimized only for the Strix Halo but llama.cpp should get you running with expert offloading no problem.


Is this the future version of holding two phones together to transmit files via infrared?


I’m running Gufo on a Strix Halo PC with 128GB shared memory.
The quant is unsloth’s UD-Q4_K_XL. Speed is really good with this configuration (1600 t/s prefill and 100 t/s decode). I wanted to try some higher quants as well but I’m waiting for Qwen 4 for now to do more testing.
You should be able to get QFN running quite well on your system as well when offloading unused experts to RAM.


I don’t know what they are testing but I use QFN for everything.
Assuming it doesn’t have to rely on internal knowledge too much by giving it tools to retrieve information, it does everything I ask it to.
Bitwarden keeps a copy of your vault on clients.
So even if you lose your Vaultwarden/Bitwarden server files, you will have a local copy on every device you use.


Fantastic news. My only gripe with 3.8 is that 262k is very limiting with all the reasoning the model does.
Pi ends up compacting history 3-4 times for larger tasks before it finishes.


You don’t have to be pro PHP to realize “PHP has not improved since 2005” is bullshit.
Did they ever say anything about removing the cyber security and reverse engineering capabilities on their smaller models (27b and Flash)?
That could end up making 3.8 more useful than 4 in those areas.