Yeah, a good rule of thumb is that the weights take up ~100% of the size of the model, so 100B bytes (8-bit quant) would be, well, 100GB and a 4-bit quant would be half that.
Yeah, a good rule of thumb is that the weights take up ~100% of the size of the model, so 100B bytes (8-bit quant) would be, well, 100GB and a 4-bit quant would be half that.
I don't know if that's, well, a rule of thumb, it might be, well, straight multiplication.
Oh, that is a useful rule to know! Thanks!
That's not exactly the math. Theres also vram needed for context. I operate several 72-128 GB machines and the larger the context the slower they go.
And the context takes space +kv cache. KV cache drives usefulness as your context grows, it needs to pull the kv cache.
Simplified, the context has to be run on every turn, so the KV cache supplies the processed tokens, so it just needs the new inpute.