| # | Tweet | Community | Topic | Views ▼ | Ratio | Engagement | Posted |
|---|---|---|---|---|---|---|---|
| 1 | [image] okay let me say this out loud again. if you want to run local models on a single RTX 3090, your best option right now is qwen 3.5 27B dense Q4_K_M. 35 tok/s, flat from 4K to 300K+ context, zero speed degradation.
thinking mode works. 262K native context on 24GB. slower than MoE | x/LocalLLaMA | Artificial Intelligence | 27.9K | 1.4x | 650 | Mar 28 |
| 2 | [image] are you on v0.5.0 too? | Hermes Agent | Software | 13.0K | 0.6x | 287 | Mar 29 |
| 3 | [image] teknium just shipped 7 pluggable memory providers. this is massive. your agent can now remember you across sessions with the backend YOU choose.
run 'hermes update' right now and then 'hermes memory setup' to pick your provider. if you're on local only, holographic uses SQLite | Hermes Agent | Software | 11.3K | 0.5x | 109 | Apr 3 |
