I wish more modern TPUs were available for purchase. Google’s TPU v8i is very powerful, but you can only rent it via Google Cloud. (that and they’re most useful in big clusters, and the pricing for such a cluster is definitely out of reach for anyone that’s not running their own data center)
Comment on Any external NPU that can be hooked to a proxmox miniPC?
yellowbadbeast@lemmy.blahaj.zone 3 days agoAny TPU you can buy is going to be essentially useless for either image diffusion or LLMs. The onboard RAM is both far too small and far too slow (LLM text generation speed relies on RAM speed first and foremost, and both LLMs and image models tend to be, you know, big), and USB isn’t nearly fast enough to help with that, Not to mention that software support is pretty much nonexistent. You’d be better off upgrading the GPU to a 3060ti 12gb or something.
P.S. A word of advice, consider using something other than Ollama. Llama.cpp in router mode or llama-swap support pretty much all of the functionality that Ollama does without being crap. Ik_llama.cpp is also nice if you have a CPU/Nvidia setup.
dan@upvote.au 2 days ago
echo@lemmy.ml 2 days ago
Qwen3.8 is out now and blows Qwen3.6 out of the water in pretty much every metric
yellowbadbeast@lemmy.blahaj.zone 2 days ago
AFAIK there isn’t a sparse 35B variant of 3.8, and I would not recommend running a dense 27B model on dual-channel DDR4 unless you are exceptionally patient.
xSikes@feddit.online 42 minutes ago
Not sure half of what you said due to I’m just getting started; but you explained that real well that I can follow. I wish I knew what you know. Thanks for sharing.