Discussion (2 Comments)Read Original on HackerNews

Pragmata•about 4 hours ago

I've been using it for the past few days, and it runs really well!

I usually get 7 token/s using llama or lm studio, but this inference recipe runs at a smooth 80 tokens per second.

Genuinely very usable, and fully local!

kristianp•about 1 hour ago

Which card are you using? I was getting about 40 with an UD q3 quant with MTP (prediction) enabled and llama.cpp compiled for my compute capability, but was very limited in the context size. I have an 4060 ti 16GB. Wouldn't recommend it as there's a tradeoff between larger context without MTP and about 18 tokens/s.

Run QWEN3.8 27B on 16gb Nvidia GPUs

⚡ Community Insights

Discussion (2 Comments)Read Original on HackerNews