I have been running 3.6 27b on a dual AMD r9700 setup using Opencode and Matt Pocock's skills workflow for writing Golang CLIs. It's decent, but won't win any awards on code architecture. I guess you can try to AGENTS.md the deficits but I am just exploring its raw Opencode experience right now. Much slower than an API but still 3x times faster than I can read. Tuning it in with a community chat template and a specific penalty for repeats was the sauce needed to get it to work. I can probably start loop daddying it now over the tickets Matt's flow creates.

So yeah, it's the best local model I've seen. I am going to try the Qwopus 3.6 fine tune soon with the same spec and tickets and compare the output of both.

Would you mind sharing more please? I literally just finished the same set up, with a 9950X CPU and 192G RAM at 4,800 MT/s. I used lemonade with Vulkan and the UD-Q8_x_x model from HF. 256k context. I have about 8G VRAM free, and use the iGPU for my desktop/monitor on Arch. What options do you give llama-cpp or whatever you run please? What other models have you found fit nicely in the 2xR9700? Thanks!!