Replying to
I use it with a standalone dash mounted screen unit, a cheap little Chinese thing that just does that and CarPlay.
Remote
Hexarei
@Hexarei@beehaw.org
0 Followers
0 Following
10 Posts
Joined June 05, 2023
Replying to
The main trouble with Stoat and Fluxer from what I've seen is that they're both trying too hard to _be_ Discord, while neither of them are quite hitting the mark. They'll be interesting to follow in the future
Replying to
I'm playing Tomodachi Life: Living the Dream with my spouse! We're playing dollies with our D&D characters lmao
Replying to
Ive had good success on similar hardware (5070 + more ram) with GLM-4.7-Flash, using llama.cpp's --cpu-moe flag - I can get up to 150k context with it at 20ish tok/sec. I've found it to be a lot better for agentic use than GPT-OSS as well, it seems to do a much more in depth reasoning effort, so while it spends more tokens it seems worth it for the end result.
Replying to
I just run the llama-swap docker container with a config file mounted, set to listen for config changes so I don't have to restart it to add new models. I don't have a guide besides the README for llama-swap.
Replying to
Can confirm, my coworkers still don’t know I’ve transitioned yet because they’re all bigots
Replying to
I step/move around the kitchen in a “flowy” way and dance to music that’s only in my head while I’m cooking or making espresso drinks at home and it brings me much joy
Replying to
run a local LLM like Claude!
Look inside
“Run ollama”
Ollama will almost always be slower than running vllm or llama.cpp, nobody should be suggesting it for anything agentic. On most consumer hardware, the availability of llama.cpp’s --cpu-moe flag alone is absurdly good and worth the effort to familiarize yourself with llamacpp instead of ollama.