- cross-posted to:
- [email protected]
- cross-posted to:
- [email protected]
A note that this setup runs a 671B model in Q4 quantization at 3-4 TPS, running a Q8 would need something beefier. To run a 671B model in the original Q8 at 6-8 TPS you’d need a dual socket EPYC server motherboard with 768GB of RAM.
Fwiw i can run the deepseek7b model with RX6600 (~$200, shud be cheaper nowadays) relatively fast, tho i haven’t used it for compiicated tasks.