|
context size vs speed in GGUF on M3 Max
|
10-19-2026, 02:50 AM
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed. I keep promising myself this is the last rebuild.
2x3090 • llama.cpp • too much VRAM is still not enough
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
context size vs speed in GGUF on M3 Max - by bytesupply76 - 10-19-2026, 03:55 AM
Re: context size vs speed in GGUF on M3 Max - by vrambandit - 10-18-2026, 10:41 PM
Re: context size vs speed in GGUF on M3 Max - by visionyard23 - 10-19-2026, 12:52 AM
Re: context size vs speed in GGUF on M3 Max - by embershed99 - 10-19-2026, 01:49 AM
Re: context size vs speed in GGUF on M3 Max - by vrambandit - 10-19-2026, 02:50 AM
Re: context size vs speed in GGUF on M3 Max - by macronest - 10-18-2026, 11:41 PM
Re: context size vs speed in GGUF on M3 Max - by mangotinker73 - 10-19-2026, 03:29 AM
Re: context size vs speed in GGUF on M3 Max - by latentcraft - 10-19-2026, 04:29 AM
Re: context size vs speed in GGUF on M3 Max - by mintstream9 - 10-19-2026, 05:46 AM
|
