Damus
Justin Moon · 7w
I want to find someone who is obsessed with local models
Fully Regarded · 7w
I’m fucking totally obsessed.
franzap · 7w
Not much. Running gpt-oss:20b via Ollama completely offline. For personal stuff I never use remote models.
sean · 7w
i've experimented a bit, lm studio, vllm, on a ryzen 5 ai + 96GB system ram, the problem isn't really the inference, it's the prefill that's super slow
lontivero · 7w
I've tried aider-chat and claude code with different local models. It worked but it took like an hour to do what I asked to do. nostr:nevent1qqsqqqzfdena73k92cwp8d3p3ucsq6dmw04a4u8pcqrg33wgq6823ncpz4mhxue69uhhyetvv9ujuerpd46hxtnfduhsygy7xr55qguvm847h33js9md6ngsnqfp99zz72nv8pe8l3n05l4fpgpsgqqqqqqsfe...
Sebastix · 7w
https://www.amd.com/en/developer/resources/technical-articles/2026/how-to-run-a-one-trillion-parameter-llm-locally-an-amd.html
someone · 7w
What do u want to know