you can give "unloading some layers to RAM" a try though.. that way you can get your hands on the "usable" 31b models. browse around to find some good 31b ones.. GL
- Posts
- 6
- Comments
- 42
- Joined
- 2 yr. ago
- Posts
- 6
- Comments
- 42
- Joined
- 2 yr. ago
LocalLLaMA @sh.itjust.works My experience with local LLM
Fediverse @lemmy.world better Mastodon feeds
Selfhosted @lemmy.world My take on Alpine as a platform for selfhosting
Selfhosted @lemmy.world Home server rebuild automation workflow
Lemmy @lemmy.ml The minimalism of Jerboa app is unparalleled
Selfhosted @lemmy.world Ditching the VPN and port forwarding the selfhosted way
cool what was your hardware, and which qwen size you used? thanks