top | item 39916918

(no title)

glintik | 1 year ago

How much RAM browser wants to run LLM local processing?

discuss

order

dchest|1 year ago

Usually around 5 GB for a 7B 4-bit quantized model.

skeeter2020|1 year ago

probably less than it needs for a few dozen open tabs based on my past profiling experiences...

kevindamm|1 year ago

How long are you willing to wait?