lain@lain@fediffusion.art: @kaiaskutes which qwen are you using? 27b?

Home | Notifications | New Note | Local | Federated | Search | Logout

Note Detail

kaiaskutes@kaiaskutes@fediffusion.art (2026-10-08 19:12:54)
I asked Muse 1.3 to help me setup Qwen 3.8 in OpenCode locally, which it did immediately, with llama-cuda.

now I'm trying out local code generation, since I have a use-case where I cannot use remote models. it does kinda work, but the context window is limited and it is quite slow.
---Reply---
lain@lain@fediffusion.art (2026-10-08 20:09:11)
@kaiaskutes which qwen are you using? 27b?


---Replies---

lain@lain@fediffusion.art (2026-10-08 20:36:14)
@kaiaskutes check out https://github.com/Niko1221/Strata, that should run qwen 3.8 fn at good speeds on your asuka card

kaiaskutes@kaiaskutes@fediffusion.art (2026-10-08 21:01:59)
@lain yes 27B, but using it for a bit, the context window is not big enough. I fell back on Chinese model via OpenRouter thinking/hoping they won't care about NSFW content.

I'll try Strata, thanks!