Ben Terhechte
banner
terhechte.bsky.social
Ben Terhechte
@terhechte.bsky.social
Swift & Rust. Formerly XING, now doing all kinds of things.

I have more side projects than are good for me. There's the markdown presentation app Hyperdeck (https://hyperdeck.io), there's the Mastodon Client Ebou and more
In addition, the model has a 10M token context window, which is huge. Not sure how well it can keep track of the context at such sizes, but just not being restricted to ~32k is already great, 256k even better.
April 5, 2025 at 6:54 PM
I just asked a local 7B model a question with a 2k context and got ~60 tokens/sec which is really fast (MacBook Pro M4 Max). So this could hit 30. Time to first token (the processing time before it starts responding) will probably still be slow because (I think) all experts have to be used for that
April 5, 2025 at 6:54 PM
Hamburg Elbe delivers
July 2, 2023 at 7:35 AM
Spotify free account playlist with occasional ads
July 2, 2023 at 7:34 AM
Lost in documentation
July 2, 2023 at 7:33 AM
Are you more active here or on mstdn? Or post everything twice?
July 2, 2023 at 7:33 AM