10-19-2026, 05:47 AM
I tested this tonight. On A6000 with TensorRT-LLM, I saw basically the same behavior. I expected the model choice to matter more than it did.
|
8B vs 14B sweet spot: anyone testing this?
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
8B vs 14B sweet spot: anyone testing this? - by torchsmith25 - 10-18-2026, 06:18 PM
Re: 8B vs 14B sweet spot: anyone testing this? - by cozywire - 10-18-2026, 05:44 PM
Re: 8B vs 14B sweet spot: anyone testing this? - by localpatch78 - 10-18-2026, 07:36 PM
Re: 8B vs 14B sweet spot: anyone testing this? - by batchsize - 10-18-2026, 09:23 PM
Re: 8B vs 14B sweet spot: anyone testing this? - by quantnest - 10-18-2026, 09:42 PM
Re: 8B vs 14B sweet spot: anyone testing this? - by plainworks - 10-19-2026, 01:45 AM
Re: 8B vs 14B sweet spot: anyone testing this? - by southspark - 10-19-2026, 02:05 AM
Re: 8B vs 14B sweet spot: anyone testing this? - by fastscope - 10-19-2026, 05:47 AM
Re: 8B vs 14B sweet spot: anyone testing this? - by forgemixer - 10-19-2026, 05:57 AM
|
Users browsing this thread: 1 Guest(s)