long context that stayed useful for Llama

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

long context that stayed useful for Llama

audiopoint18 Offline

Junior Member

Posts: 45
Threads: 6
Joined: Sep 2026
Reputation: 0

09-23-2026, 06:59 AM

Maybe, but I had the opposite result. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

Find

« Next Oldest | Next Newest »

Messages In This Thread

long context that stayed useful for Llama - by emberquill - 09-17-2026, 10:07 PM

Re: long context that stayed useful for Llama - by syshouse - 09-18-2026, 06:47 AM

Re: long context that stayed useful for Llama - by sanescope - 09-18-2026, 07:28 AM

Re: long context that stayed useful for Llama - by plainember52 - 09-23-2026, 10:24 AM

Re: long context that stayed useful for Llama - by bytesupply76 - 09-18-2026, 08:19 PM

Re: long context that stayed useful for Llama - by torchkite - 09-19-2026, 08:29 PM

Re: long context that stayed useful for Llama - by cozywire - 09-19-2026, 09:08 PM

Re: long context that stayed useful for Llama - by tinycontext - 09-23-2026, 02:40 PM

Re: long context that stayed useful for Llama - by llm_wren - 09-23-2026, 03:07 PM

Re: long context that stayed useful for Llama - by quantyard - 09-22-2026, 09:41 PM

Re: long context that stayed useful for Llama - by quiethouse - 09-23-2026, 06:13 AM

Re: long context that stayed useful for Llama - by audiopoint18 - 09-23-2026, 06:59 AM

Re: long context that stayed useful for Llama - by tinycontext - 09-23-2026, 07:17 AM

Re: long context that stayed useful for Llama - by vectorpoint - 09-23-2026, 09:39 AM

Re: long context that stayed useful for Llama - by sanescope - 09-23-2026, 11:20 PM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)

Login
Username:
Password:	Lost Password?
	Remember me

Sign in with X.com