Local models are meaningfully useful* for agentic work now. This is a realization I came to over the last day or so.
I wrote a lot of custom mods for a game that recently switched engines. The migration is going rather smooth for most people because of wise architectural choices from the dev early on, and because they prioritized backwards compatibility in the update. But there are still some rough edges, especially if you had your hooks deep into the engine.
I recently vibeforked Unbiased Bob's fork of Strata to make it compatible, easy to use and optimized for my OS and hardware (NixOS 5800x3d 64gb, 7900xtx 24gb). Sol 6.1 got it working with Qwen 3.8 Flash Next IQ3 XSS (~75GB) at roughly 46tps 164k ctx with enough headroom to launch a heavy browser along with a triple-A game set to low in 720p for testing when I need to (plus space for zram swap)
I set it up in deepseek harness, gave it a 14MB error log in the game's working directory, then went to sleep. I woke up and it had run for 3 hours. The game launched with only two errors, which it quickly fixed from the new, vastly smaller logfile.
It hammered down every issue, making changes across 30 separate mod repos. Practically a one-shot, and all the features worked as originally intended.
I left a local coding agent running completely on its own for three hours across multiple repos across a dozen auto-compactions with a log file and no ability for it to verify its work besides a compiler. And it produced meaningful results. I can't speak to the code quality, but it worked. This was completely unthinkable even just two years ago. Even one year ago, the cloud frontier wouldn't be able to do this on its own, and now a local model can, running on my consumer gaming hardware from one or two gens back.
“Huh... So... We're here now..." I said to myself, with a bit of stunned disbelief, wondering what the future one or two years from now might hold.
Its nice to read something positive about AI, I used a model to get Stalker 2 running smoothly (using optiscaler)
I recently got a laptop GPU with 16gbs Vram - what models do you guys recommend?
Ive been testing this: https://ollama.com/edtorre/qwen3.5-hermes
This person on huggingface makes excellent space saving models using APEX quantizations. They produced this one to fit on gpus with 16gb of vram or less.
https://huggingface.co/mudler/Qwen3.8-27B-APEX-GGUF
Really depends on how much headroom you need and your system ram and the PCIe / vram speed because I got a friend with a pcie5 16gb gpu and 64gb of system ram that's getting slightly better performance than me using the same setup, despite half the vram.
If you want speed and not a ton of intelligence, the 3.6 30B A3B runs fast. If you need smarts, then either a qwen 3.8 27b (probably a thinking cap finetune) or try flash next (swift finetune) in unbiased strata if you don't mind taking a risk and burning some bandwidth on a 75-85GB model that might not run great. In either case, be sure to use MTP and the model card inference params