I want to download the goliath model but I can only afford Q3_K_M. It is written that it has high quality losses. How much quality loss is there?
I heard that the larger the model, the less it suffers intellectually when it is optimized. I usually use 70B Q5_K_M. Can I expect that 120B Q3_K_M will be significantly better than 70B Q5_K_M so that the time spent on downloading will be worth it?
How you actually use it at home ? 3 or 4 old Test P40 from ebuy/local alternatives? Just CPU?
4x3090s will run it at over 4bits.
I imagine it’s pretty solid.
I’ve tested around the with q4_K_M and the q8 on my Mac Studio, and the q4 is pretty darn good. There’s some difference in that the q4 does seem to get confused when I talk to it sometimes, whereas the q8 seems unshakeable in its quality, but honestly the q4 still feels better than almost any other model I’ve ever used.
What’s the tok/s for each of those models on that system?
Edit: also, if you don’t mind my asking, how much context are you able to use before inference degrades?
for comparison sake EXL2 4.85bpw version runs around 6-8 t/s on 4x3090s at 8k context it’s the lower end.
What software are you using to run Goliath on? Using a Mac Studio I get errors in LM Studio and text-generation-webui and can’t load any of the blokes gguf’s for it. I can only load the 2bit from the creator. Any help would be much appreciated. Thanks!