Yeah 48g, sub 200W seems like a sweet spot for a single card setup. Then you can stack as deep as you want to get the size of model you want for whatever you want to pay for the power bill.
Used 3090s have been getting expensive in some markets. Another option is dual 5060ti 16 gig. Mine are lower powered, single 8 pin power, so they max out around 180W. With that I'm getting 80t/s on the new qwen 3 30b a3b models, and around 21t/s on Gemma 27b with vision. Cheap and cheerful setup if you can find the cards at MSRP.
About 768 gigs of ddr5 RAM in a dual socket server board with 12 channel memory and an extra 16 gig or better GPU for prompt processing. It's a few grand just to run this thing at 8-10 tokens/s
These articles are gold, thank you. I used your gemma one from a few weeks back to get gemma 3 performing properly. I know you guys are all GPU but do you do any testing on CPU/GPU mixes? I'd like to see the pp and t/s on pure 12 channel epyc and the same with using a 24 gig gpu to accelerate the pp.
Qwen is a little fussy about the sampler settings, but it does run well quantized. If you were getting infinite repetition loops, try dropping the top_p a bit. I think qwen likes lower temps too
You probably won't be running fp16 anything locally. We typically run Q5 or Q6 quants to maximize the size of the model and context length we can run with the VRAM we have available. The quality loss is negligable at Q6.
It's a 3b model so the creativity is pretty limited. What helped for me was prompting for specific stories in specific styles. I have a python script that randomizes the prompt and the writing style, including asking for specific author styles.
I have a mini PC with an n100 CPU connected to a small 7" monitor sitting on my desk, under the regular PC. I have llama 3b (q4) generating endless stories in different genres and styles. It's fun to glance over at it and read whatever it's in the middle of making. I gave llama.cpp one CPU core and it generates slow enough to just read at a normal pace, and the CPU fans don't go nuts. Totally not productive or really useful but I like it.
I had this same issue with incomplete answers on longer summarization tasks. If you ask it to "go on" it will produce a better completion, but I haven't seen this behaviour in any other model.