chzblck
Joined 4 years ago
Joined 4 years ago
I get great results and save tokens
On a 64gb Ram and 5080 machine the biggest model suggested was Qwen 9B
can hit 90+ tps on the MoE 35b but mag thinks it wont fit.
Last night I was able to give claude a task and they increased the classification accuracy from
81.3/89.9/92.1 to 90.9/99.3/99.6
In a little over 2 hours. In a task that up until opus 5.5 I was doing by hand/manually. and the day before was able to get the first results.
The intelligence explosion may just be user error.
For mine I was on the fence - waited an hour or so and the delivery date went from early oct to 10-12 weeks so i decided to wait on the 512gb version
"One of the nice things God does, is that he doesn't let people who don't have kids know what they're missing"
Lets add Facebook, twitter, openai, claude + all the others.
then lets add Flock, Palantir.
Do you honestly think the lobbying from them would be more or less if this bill gained any traction?