Sad. Qwen3.8 27B IQ3_XXS isn't living up to my exp...
# random
s
Sad. Qwen3.8 27B IQ3_XXS isn't living up to my expectations. It looks like I'm unable to find a good local LLM for 16 GB of VRAM. I'm starting to think there simply isn't one. I keep repeating...
GPT-OSS-20B is a really fast model, but since it's not following instructions it's not useful at all for coding. It just skips all checks, so at the end its output doesn't even compile.
I ended up subscribing to z.ai GLM Coding Lite for $18/month
Why do I even try to fiddle with local models?
I find ZCode to a pretty good harness.