This initial round of benchmarking was to understand if there was any usecase here at all and I think there is. In a follow up, I'll be trying to answer questions like this. How big of a model can you fit on 4x M60, 4x P100, 4x V100? What are the tok/second when varying context length?
Do you have a set of models you'd like me to look at?
That's great. Personally, I'd interested in Qwen3.6-27B and deepseek V4 flash (or pro), with contexts above 60k. They seem to be popular and have good coding performance. I'd appreciate numbers on a single or two GPUs where a quantized version fits reasonably into the VRAM (Qwen in 16 or 24GB). 4 older GPUs approach a used 3090 in price, and the 3090 has better support for speedups like MTP. So cheaper but slower looks like a reasonable target to me.
No problem. Varying context size is a common request I've been getting as well. Personally I'm looking forward to seeing how much we can cram into the ancient K80's 24GB of VRAM :0
Similar interest here, possibly including if qwen 3.6, Gemma4 or DiffusionGemma (with the largest quants that will fit in a single card) will offer, say,
50 tokens-per-second (fast enough for interactive human-in-the-loop code research, print-f iterations on code to debug things, etc; or let the LLM churn on a problem for a minute while I step out to handle something else), context of up to 200k preferred.
Also if nothing else the below project lets you use an NVidia graphics card as low-latency swap, which has been nice as a buffer as RAM prices remain high and leaves me eyeing that 24GB card you mentioned as an alternative...
Have a look at Donato Capitella's video: https://m.youtube.com/watch?v=zp8j4vO-wz0
He provides also toolboxes and benchmark tables as text (in the video description)
Do you have a set of models you'd like me to look at?