0.2 tok/s is fine for experimentation, but it is not interactive in any meaningful sense. For many use cases, a well-quantized 8B or 13B that stays resident will simply deliver a better latency-quality tradeoff
You can get lots of tokens per second on the CPU if the entire network fits in L1 cache. Unfortunately the sub 64 kiB model segment isn't looking so hot.
But actually ... 3000? Did GP misplace one or two zeros there?
Do you have $2/hr to rent an RTX 6000 96GB or $5/hr for B200 180GB on the cloud?
But 5 seconds / token is quite slow yeah. I guess this is for low ram machines? I'm pretty sure my 5950x with 128 gb ram can run this faster on the CPU with some layers / prefill on the 3060 gpu I have.
I also see that they claim the process is compute bound at 2 seconds/token, but that doesn't seem correct with a 3090?
DDR4 tops out about 27Gbs
DDR5 can do around 40Gbs
So for 70B model at 8 bit quant, you will get around 0.3-0.5 tokens per second using RAM alone.
In general systems usually have PCIE version with bandwidth better than RAM of that system.
For example a system with DDR4 (27Gbs) usually has at least PCIE4 (32Gbs at 16x).
But you can bottleneck that by building a DDR5 (40Gbs) system with PCIE4 card.
LLama 3.1 however is not MoE, so all params are active.
For MoE it is tricky, because for each token you only use a subset of params (an “expert”) but you don’t know which one, so you have to keep them all in memory or wait until it loads from slower storage, potentially different for each token.