Comment by reactordev
9 hours ago
yes, I average 80-120 tok/s on my RTX 3080 with gemma 4 and faster with Qwen 3.5. The main use-case here is just code-monkey agents. I'm not looking for architectural guidance, but an agent to take a spec and complete it.
And is this using conventional model loading (all in VRAM), or are you streaming it in some way?