[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
Jason @foley2k2 on x 1281 followers
Created: 2025-07-16 23:55:56 UTC
@illscience We need efficient, capable local models. Something like 25b parmeters XX tokens/sec, 256k context on 24gb vram and an intelligence score above XX.
Reducing it to single language support might help. (i. e. English python)
$200/mo for a year is a GPU.
XXX engagements
